inputs
stringlengths 84
563k
| targets
stringlengths 0
13.8k
| task_source
stringclasses 1
value | task_name
stringclasses 849
values | template_type
stringclasses 2
values |
|---|---|---|---|---|
Instructions: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
Input: How many MW is the power station formally listed on the stock exchanges of Pakistan in 2005 ?
Output: | 1,600 | NIv2 | task344_hybridqa_answer_generation | zs_opt |
In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
Example input: Who were the builders of the mosque in Herat with fire temples ?
Example output: Ghurids
Example explanation: This is a good example. Ghurids were the builders of the mosque in Herat with fire temples.
Q: How many MW is the power station formally listed on the stock exchanges of Pakistan in 2005 ?
A: | 1,600 | NIv2 | task344_hybridqa_answer_generation | fs_opt |
Teacher:In this task, you're given a question, a context passage, and four options which are terms from the passage. After reading a passage, you will get a brief understanding of the terms. Your job is to determine by searching and reading further information of which term you can answer the question. Indicate your choice as 'a', 'b', 'c', or 'd'. If you think more than one option is plausible, choose the more probable option to help you answer the question.
Teacher: Now, understand the problem? Solve this instance: Question: What year was the venue where Potter made his theatrical debut constructed? Passage:Potter was born in Bedford to Reverend Brignal Peel, a Wesleyan minister, and Elizabeth Stimson. He was educated at Bedford Modern School and for a time at Worcester College, Oxford. He first performed in E. M. Royle's The White Man at the Lyric Theatre in London before touring. In 1915 he was George Robey's understudy at the Alhambra. During the Great War Potter served as a 2nd lieutenant in the Royal Field Artillery in France. He served in the 6th Division 2nd Brigade 21st Battery, from 8 February 1917 before returning to music hall once the war was over. Potter cultivated an individual style and persona, wearing a straw boater, wide grey flannel trousers (he said he invented the Oxford bags style at the Coliseum in 1920), an 'Old Borstolian' blazer and carrying a notebook with a rolled umbrella. James Agate described him as "that sham Harrovian who bears upon his blazer the broad arrows of a blameful life".
Links: a. World War I b. Music hall c. Bedford d. Lyric Theatre, London
Student: | d | NIv2 | task231_iirc_link_classification | zs_opt |
Q: In this task, you will be presented with a text and a pronoun. You should write an implausible answer to the question of what is the pronoun's reference. Even though there exist multiple wrong answers, we only need a single wrong answer. Position of the pronoun in the text is showed within two "_"s.
Thomas Hermanns (b. 5 March 1963) is a German TV-presenter, director, TV-author and comedian. _He_is known for his comedy-show Quatsch Comedy Club. <sep>, Pronoun: He
A: | TV-presenter | NIv2 | task331_gap_incorrect_answer_generation | zs_opt |
In this task, you're given a question, a context passage, and four options which are terms from the passage. After reading a passage, you will get a brief understanding of the terms. Your job is to determine by searching and reading further information of which term you can answer the question. Indicate your choice as 'a', 'b', 'c', or 'd'. If you think more than one option is plausible, choose the more probable option to help you answer the question.
One example: Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-Lôduring July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,
. Links: a. Allies of World War II b. Wesel c. Operation Market Garden d. Air Support.
Solution is here: c
Explanation: The passage describes the 704th's actions during Operation Market Garden.
Now, solve this: Question: What year was the venue where Potter made his theatrical debut constructed? Passage:Potter was born in Bedford to Reverend Brignal Peel, a Wesleyan minister, and Elizabeth Stimson. He was educated at Bedford Modern School and for a time at Worcester College, Oxford. He first performed in E. M. Royle's The White Man at the Lyric Theatre in London before touring. In 1915 he was George Robey's understudy at the Alhambra. During the Great War Potter served as a 2nd lieutenant in the Royal Field Artillery in France. He served in the 6th Division 2nd Brigade 21st Battery, from 8 February 1917 before returning to music hall once the war was over. Potter cultivated an individual style and persona, wearing a straw boater, wide grey flannel trousers (he said he invented the Oxford bags style at the Coliseum in 1920), an 'Old Borstolian' blazer and carrying a notebook with a rolled umbrella. James Agate described him as "that sham Harrovian who bears upon his blazer the broad arrows of a blameful life".
Links: a. World War I b. Music hall c. Bedford d. Lyric Theatre, London
Solution: | d | NIv2 | task231_iirc_link_classification | fs_opt |
Detailed Instructions: Given a scientific question, generate a correct answer to it.
Problem:Skeletal muscle cells and cardiac muscle cells share what property, which is not shared by smooth muscle cells?
Solution: | striations | NIv2 | task591_sciq_answer_generation | zs_opt |
You are given an amazon food product review and its polarity (positive or negative). Your task is to answer "True" if the specified sentence and its polarity match; otherwise, answer "False".
Great value and much superior to what you find in stores. Makes a great snack or after dinner treat, but for those who are health conscious remember to keep it to a few pieces since they are covered in thin sugar. Try to keep the bag tightly sealed once you open them since the slowly begin to dry up. Will be ordering more soon :)
Polarity: Negative | False | NIv2 | task587_amazonfood_polarity_correction_classification | zs_opt |
You will be given a definition of a task first, then some input of the task.
Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].
What is the sentiment of the following document towards the entity Nikolas Cruz ? BREAKING: Spokesperson for white supremacist group Republic of Florida admitted to ADL that Nikolas Cruz alleged perpetrator of deadly Parkland school shooting was a member & trained with his group which seeks to create a âwhite ethnostate.â More info: [Link] â Jonathan Greenblatt (@JGreenblattADL) February 15 2018
Output: | Neutral | NIv2 | task421_persent_sentence_sentiment_classification | zs_opt |
Part 1. Definition
In this task, you will be presented with a text and a pronoun. You should write an implausible answer to the question of what is the pronoun's reference. Even though there exist multiple wrong answers, we only need a single wrong answer. Position of the pronoun in the text is showed within two "_"s.
Part 2. Example
He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His
Answer: Bernard Leach
Explanation: Based on the text, his refers to MacKenzie and Bernard Leach is a good incorrect answer.
Part 3. Exercise
Thomas Hermanns (b. 5 March 1963) is a German TV-presenter, director, TV-author and comedian. _He_is known for his comedy-show Quatsch Comedy Club. <sep>, Pronoun: He
Answer: | TV-presenter | NIv2 | task331_gap_incorrect_answer_generation | fs_opt |
In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
Example Input: The Mclaren/Mercedes constructor who is nickname the `` The Flying Finn '' , how many formula one grand prix wins ?
Example Output: 2
Example Input: Which football club is the oldest professional club of any football code ?
Example Output: Melbourne
Example Input: How many MW is the power station formally listed on the stock exchanges of Pakistan in 2005 ?
Example Output: | 1,600
| NIv2 | task344_hybridqa_answer_generation | fs_opt |
Definition: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.
Input: Title: Nap Time. Sentence 1: My 2 year old daughter hates naps. Sentence 2: Today she hid under the bed. Sentence 3: Every day she tries to trick me into letting her stay awake. Sentence 4: I let her stay under there. Sentence 5: She ended up taking a nap under the bed instead!
Output: | 32 | NIv2 | task218_rocstories_swap_order_answer_generation | zs_opt |
In this task, you will be presented with a question in Persian. Based on the knowledge you need to answer the question, classify the question into "math_and_logic", "literature", or "common_knowledge".
Q: کدام کتاب اثر ویکتور هوگو نیست؟
A: | literature | NIv2 | task474_parsinlu_mc_classification | zs_opt |
Given a scientific question, generate a correct answer to it.
Let me give you an example: Who proposed the theory of evolution by natural selection?
The answer to this example can be: darwin
Here is why: This is a direct fact that Charles Darwin proposed the theory of evolution.
OK. solve this:
Skeletal muscle cells and cardiac muscle cells share what property, which is not shared by smooth muscle cells?
Answer: | striations | NIv2 | task591_sciq_answer_generation | fs_opt |
Q: In this task, you need to count the number of nouns/verbs in the given sentence.
Sentence: 'A closeup of a pizza with whole tomato slices'. Count the number of nouns in this sentence.
A: | 4 | NIv2 | task155_count_nouns_verbs | zs_opt |
Detailed Instructions: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
Problem:What company took over the station with the lowest UHF number ?
Solution: | Viacom | NIv2 | task344_hybridqa_answer_generation | zs_opt |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
You are given an amazon food product review and its polarity (positive or negative). Your task is to answer "True" if the specified sentence and its polarity match; otherwise, answer "False".
I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most.
Polarity: Positive
Solution: True
Why? It's a positive review because the owner of the dog is satisfied with the product and mentioned that their dog appreciates the product. Also, the polarity is positive. So, the correct answer is True.
New input: Great value and much superior to what you find in stores. Makes a great snack or after dinner treat, but for those who are health conscious remember to keep it to a few pieces since they are covered in thin sugar. Try to keep the bag tightly sealed once you open them since the slowly begin to dry up. Will be ordering more soon :)
Polarity: Negative
Solution: | False | NIv2 | task587_amazonfood_polarity_correction_classification | fs_opt |
Given the task definition, example input & output, solve the new input case.
Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].
Example: What is the sentiment of the following sentence towards the entity Bill Clinton ? Bill Clinton knows how to win friends and influence people.
Output: Positive
Here the author of the document praises Bill for this ability to win friends.
New input case for you: What is the sentiment of the following document towards the entity Nikolas Cruz ? BREAKING: Spokesperson for white supremacist group Republic of Florida admitted to ADL that Nikolas Cruz alleged perpetrator of deadly Parkland school shooting was a member & trained with his group which seeks to create a âwhite ethnostate.â More info: [Link] â Jonathan Greenblatt (@JGreenblattADL) February 15 2018
Output: | Neutral | NIv2 | task421_persent_sentence_sentiment_classification | fs_opt |
Teacher: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.
Teacher: Now, understand the problem? If you are still confused, see the following example:
Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: The pair he bought fit him perfectly. Sentence 3: He decided to buy a pair of khakis. Sentence 4: All of his clothes were either too formal or too casual. Sentence 5: Marcus was happy to have the right clothes for the event.
Solution: 24
Reason: Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction.
Now, solve this instance: Title: Nap Time. Sentence 1: My 2 year old daughter hates naps. Sentence 2: Today she hid under the bed. Sentence 3: Every day she tries to trick me into letting her stay awake. Sentence 4: I let her stay under there. Sentence 5: She ended up taking a nap under the bed instead!
Student: | 32 | NIv2 | task218_rocstories_swap_order_answer_generation | fs_opt |
In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding "Yes". Otherwise, respond "No". There are only two types of responses possible:"Yes" and "No".
Paragraph- Sent 1: Fatty plays a somewhat lazy young man who disrupts his mother 's life by causing a fire by smoking in bed , then ruins laundry day by dropping it in the mud .
Sent 2: He has two loves of his life , the girl next door Lizzie and his dog Luke .
Sent 3: After showcasing his lack of talents helping his mother , he is able to save Luke from the dog catchers and express his love for Lizzie through a hole in the fence .
Sent 4: In the second reel , Fatty , Lizzie , mom and Luke go to the amusement park , where Fatty is first outwitted by a couple of sharks but then retrieves his losses by pointing a fake gun at them .
Sent 5: To extract revenge , they kidnap Lizzie with the help of the embittered dog catchers , and take her to an abandoned shack , where they tie her to a post with a gun attached to a timer pointed at her head .
Sent 6: Plucky pup Luke follows the crooks , and is able to warn Fatty in time to perform the last-minute rescue , with the help of the Keystone Cops .
Sent 7: In the closing shot Fatty , Lizzie and Luke embrace in a joint kiss .
Question: Who expresses his love for Lizzie through a hole in the fence?
Incorrect Answer: luke. | No. | NIv2 | task057_multirc_classify_incorrect_answer | zs_opt |
Detailed Instructions: In this task, you will be presented with a question in Persian. Based on the knowledge you need to answer the question, classify the question into "math_and_logic", "literature", or "common_knowledge".
See one example below:
Problem: عدد 30 را بر نیم تقسیم می کنیم و سپس عدد 10 را به آن اضافه می کنیم. نتیجه کدام گزینه است؟
Solution: math_and_logic
Explanation: This is a good example. You need mathematical knowledge to answer this question.
Problem: کدام کتاب اثر ویکتور هوگو نیست؟
Solution: | literature | NIv2 | task474_parsinlu_mc_classification | fs_opt |
Definition: In this task, you are given a passage which has a question and the context. You have to generate an answer to the question based on the information present in the context.
Input: Context: Aggressive periodontitis is characterized by rapid destruction of periodontal tissue caused by Aggregatibacter actinomycetemcomitans. Interleukin (IL)-1β is a proinflammatory cytokine, and its production is tightly regulated by inflammasome activation. Xylitol, an anticaries agent, is anti-inflammatory, but its effect on inflammasome activation has not been researched. This study investigates the effect of xylitol on inflammasome activation induced by A. actinomycetemcomitans.', 'The differentiated THP-1 macrophages were stimulated by A. actinomycetemcomitans with or without xylitol and the expressions of IL-1β and inflammasome components were detected by real time PCR, ELISA, confocal microscopy and Immunoblot analysis. The effects of xylitol on the adhesion and invasion of A. actinomycetemcomitans to cells were measured by viable cell count.', 'A. actinomycetemcomitans increased pro IL-1β synthesis and IL-1β secretion in a multiplicity of infection- and time-dependent manner. A. actinomycetemcomitans also stimulated caspase-1 activation. Among inflammasome components, apoptosis-associated speck-like protein containing a CARD (ASC) and absent in melanoma 2 (AIM2) proteins were upregulated by A. actinomycetemcomitans infection. When cells were pretreated with xylitol, proIL-1β and IL-1β production by A. actinomycetemcomitans infection was significantly decreased. Xylitol also inhibited ASC and AIM2 proteins and formation of ASC puncta. Furthermore, xylitol suppressed internalization of A. actinomycetemcomitans into differentiated THP-1 macrophages without affecting viability of A. actinomycetemcomitans within cells.\Question: Does aggregatibacter actinomycetemcomitans-Induced AIM2 Inflammasome Activation be Suppressed by Xylitol in Differentiated THP-1 Macrophages?
Output: | A. actinomycetemcomitans induced IL-1β production and AIM2 inflammasome activation. Xylitol inhibited these effects, possibly by suppressing internalization of A. actinomycetemcomitans into cells. Thus, this study proposes a mechanism for IL-1β production via inflammasome activation and discusses a possible use for xylitol in periodontal inflammation caused by A. actinomycetemcomitans. | NIv2 | task849_pubmedqa_answer_generation | zs_opt |
Instructions: In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.
Input: Rihanna says that she she still loves ex-boyfriend Chris Brown despite him attacking her in 2009.
Output: | Rihanna 'still loves' Chris Brown after assault | NIv2 | task1358_xlsum_title_generation | zs_opt |
In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.
Q: [['Cotto', 'eatType', 'coffee shop'], ['Cotto', 'priceRange', 'moderate'], ['Cotto', 'customer rating', '3 out of 5'], ['Cotto', 'area', 'city centre'], ['Cotto', 'near', 'The Portland Arms']]
A: | Situated near The Portland Arms on the riverfront, north of the City centre, the 3-star '_____' coffee shop serves a range of moderately-priced fast foods. | NIv2 | task1407_dart_question_generation | zs_opt |
Given the task definition and input, reply with output. In this task, you are given a question and an answer. Answer "Yes" if the given answer correctly answers the question, otherwise answer "No".
how old is the singer bob seger, Answer: As a locally successful Detroit-area artist, he performed and recorded as Bob Seger and the Last Heard and Bob Seger System throughout the 1960s.
| No | NIv2 | task1294_wiki_qa_answer_verification | zs_opt |
Teacher:In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form " A >Causes> B". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).
Teacher: Now, understand the problem? Solve this instance: story: David had a bad toothache. He made an appointment with the dentist. The next week the dentist had to pull his tooth. David went home very sore to recover. The next day David felt much better without the pain.
selected sentence: The next week the dentist had to pull his tooth.
Student: | The dentist has to pull his tooth >Causes> David feel(s) pained | NIv2 | task749_glucose_reverse_cause_emotion_detection | zs_opt |
Q: In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
RT @HeidiL_RN: Fuck Islam you pigfucking trash troll. @ItsJustMe7o7 @MzKeriEvans @ctbauza
A: | Yes | NIv2 | task609_sbic_potentially_offense_binary_classification | zs_opt |
Detailed Instructions: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.
Problem:Sentence1: Booking was successful. The table will be reserved for 15 minutes. Reference number is : IMSY2GMJ . Is there anything else I can do for you today? Sentence2: Two people at 11:15 for 2 people. Sentence3: What day would you like to book your reservation? Sentence4: No, thank you Sentence5: Have a great day! Sentence6: I found one for you called restaurant alimentum. Would you like me to book it for you? Sentence7: Yes! Sentence8: I am looking for a local restaurant in the south that offers modern European cuisine Sentence9: For which day shall I book the table? Sentence10: Tuesday, please. Question: Who has spoken the sentence 8? (A) User (B) System
Solution: | Answer: (A) User | NIv2 | task638_multi_woz_classification | zs_opt |
Detailed Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Q: Head: PersonX offer PersonY a position<sep>Tail: some help
A: | Yes | NIv2 | task1201_atomic_classification_xintent | zs_opt |
In this task, you're given a question, a context passage, and four options which are terms from the passage. After reading a passage, you will get a brief understanding of the terms. Your job is to determine by searching and reading further information of which term you can answer the question. Indicate your choice as 'a', 'b', 'c', or 'd'. If you think more than one option is plausible, choose the more probable option to help you answer the question.
[EX Q]: Question: What year did the newspaper who called Krul an excellent reserve goalkeeper first found? Passage:Krul returned to Newcastle as backup to first choice Steve Harper. He made his senior league debut on 8 August 2009 in the opening Football League Championship game of the season away to West Bromwich Albion, coming on as a half time substitute for the injured Harper. Following this match, The Guardian called him "an excellent reserve goalkeeper". He later played the full Football League Cup match against Huddersfield Town on 26 August 2009, which Newcastle won 4–3. Krul also started the 2–0 League Cup defeat to Peterborough. Against Swansea City on 28 November, he again came on to replace the injured Steve Harper. On 2 January, he played in the FA Cup Third Round tie against Plymouth Argyle, the game ending 0–0. He then played in the replay at St James' Park on 13 January, a 3–0 victory. Krul started his first league game for Newcastle on 2 May 2010, the last day of the Championship campaign, against Queens Park Rangers at Loftus Road and kept a clean sheet. In July 2010, Krul signed a new four-year contract with Newcastle.
Links: a. St James' Park b. Steve Harper c. The Guardian d. EFL Championship
[EX A]: c
[EX Q]: Question: When was the country that was represented particularly well in the hip hop movement founded? Passage:Latinos, particularly Puerto Ricans, were at the forefront of the hip hop movement, however; they have often been forgotten in conversation. Nonetheless, we can see the presence and influence of Latinos in hip hop when we think about artist like: Africa Bambaataa & the members of the Zulu Nation (1960s), Latino DJ, DJ Disco Wiz (aka first Latino DJ in hip hop) & DJ Grandmaster Caz came together to form the Mighty Force (1974), DJ Charlie Chase of the Cold Crush Brothers (1975), Lee Quiñones & Lady Pink (1970s), and various others have allowed for Latinos to have a part in hip hop culture and hip hop history. Latina's also had a huge role in hip hop, women who were not on the hip hop stage take part in: the influence and making of music and hip hop performance, dancing of music, and graffiti art. Today we see Latinas like: La Caballota aka Ivy Queen (1995), Ana Bijoux (1995), Angie Martinez: "The Voice of New York" (1996), Hurricane G aka Gloria Rodriguez (1997), Mala Rodríguez (1990s), Lisa M: "The Queen of Spanish Rap" (1988), Nina Dioz (2009), Snow Tha Product aka Claudia Feliciano (2011), Mélony Redondo: MelyMel (2018) have been women who have all taken the stage and made their mark as Latina and Afro-Latina rappers/artist in the hip hop world.
Links: a. Ivy Queen b. Angie Martinez c. Ivy Queen d. Puerto Ricans
[EX A]: d
[EX Q]: Question: What year was the venue where Potter made his theatrical debut constructed? Passage:Potter was born in Bedford to Reverend Brignal Peel, a Wesleyan minister, and Elizabeth Stimson. He was educated at Bedford Modern School and for a time at Worcester College, Oxford. He first performed in E. M. Royle's The White Man at the Lyric Theatre in London before touring. In 1915 he was George Robey's understudy at the Alhambra. During the Great War Potter served as a 2nd lieutenant in the Royal Field Artillery in France. He served in the 6th Division 2nd Brigade 21st Battery, from 8 February 1917 before returning to music hall once the war was over. Potter cultivated an individual style and persona, wearing a straw boater, wide grey flannel trousers (he said he invented the Oxford bags style at the Coliseum in 1920), an 'Old Borstolian' blazer and carrying a notebook with a rolled umbrella. James Agate described him as "that sham Harrovian who bears upon his blazer the broad arrows of a blameful life".
Links: a. World War I b. Music hall c. Bedford d. Lyric Theatre, London
[EX A]: | d
| NIv2 | task231_iirc_link_classification | fs_opt |
In this task, you will be presented with a text and a pronoun. You should write an implausible answer to the question of what is the pronoun's reference. Even though there exist multiple wrong answers, we only need a single wrong answer. Position of the pronoun in the text is showed within two "_"s.
--------
Question: Other sources have explained Powell's injury differently; Miles Davis said Powell was beaten by a Savoy Ballroom bouncer after walking in the club without any money, while Dexter Gordon claimed he was beaten while in police custody after his arrest for drunk and disorderly conduct in a Philadelphia train station. Monk recorded ``In Walked Bud'' several times during his career, starting with the 1947 sessions later compiled for Genius of Modern Music (1951). According to music critic Robert Christgau, Monk's rendition of the song for _his_ 1958 live album Misterioso featured ``a long, laconically hilarious (and laconically, hilariously virtuosic) Johnny Griffin solo that's a landmark of saxophony''. <sep>, Pronoun: his
Answer: Robert Christgau
Question: Her mother, Frances Antoinette Johnston, had been a congressional journalist and dramatic critic for the Baltimore Sun and her daughter built on her familiarity with the Washington political scene by becoming official White House photographer for the Harrison, Cleveland, McKinley, ``TR'' Roosevelt, and Taft presidential administrations. Johnston also photographed the famous American heiress and literary salon socialite Natalie Barney in Paris but perhaps _her_ most famous work, shown here, is her self-portrait of the liberated ``New Woman'', petticoats showing and beer stein in hand. <sep>, Pronoun: her
Answer: Natalie Barney
Question: Thomas Hermanns (b. 5 March 1963) is a German TV-presenter, director, TV-author and comedian. _He_is known for his comedy-show Quatsch Comedy Club. <sep>, Pronoun: He
Answer: | TV-presenter
| NIv2 | task331_gap_incorrect_answer_generation | fs_opt |
Part 1. Definition
In this task, you need to count the number of nouns/verbs in the given sentence.
Part 2. Example
Sentence: 'A small toy kept on tray held by a man'. Count the number of nouns in this sentence.
Answer: 3
Explanation: The words 'toy', 'tray', and 'man' are nouns in this sentence. So, the answer is 3.
Part 3. Exercise
Sentence: 'A closeup of a pizza with whole tomato slices'. Count the number of nouns in this sentence.
Answer: | 4 | NIv2 | task155_count_nouns_verbs | fs_opt |
TASK DEFINITION: Given a scientific question, generate a correct answer to it.
PROBLEM: A mixture of a metal with one or more other elements is called?
SOLUTION: an alloy
PROBLEM: The nitrogen that enters living systems by nitrogen fixation is successively converted from organic nitrogen back into nitrogen gas by what?
SOLUTION: bacteria
PROBLEM: Skeletal muscle cells and cardiac muscle cells share what property, which is not shared by smooth muscle cells?
SOLUTION: | striations
| NIv2 | task591_sciq_answer_generation | fs_opt |
You will be given a definition of a task first, then some input of the task.
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
['over', '2,000', 'years', 'ago', 'Euclid', 'showed', 'every', 'number', 'has', 'exactly', 'one', 'prime', 'factorization', 'which', 'we', 'can', 'think', 'of', 'as', 'a', 'secret', 'key', 'it', 'turns', 'out', 'that', 'prime', 'factorization', 'is', 'a', 'fundamentally', 'hard', 'problem', "let's", 'clarify', 'what', 'we', 'mean', 'by', 'easy', 'and', 'hard', 'by', 'introducing', "what's", 'called', 'time', 'complexity', 'we', 'have', 'all', 'multiplied', 'numbers', 'before', 'and', 'each', 'of', 'us', 'has', 'our', 'own', 'rules', 'for', 'doing', 'so', 'in', 'order', 'to', 'speed', 'things', 'up', 'if', 'we', 'program', 'a', 'computer', 'to', 'multiply', 'numbers', 'it', 'can', 'do', 'so', 'much', 'faster', 'than', 'any', 'human', 'can', 'here', 'is', 'a', 'graph', 'that', 'shows', 'the', 'time', 'required', 'for', 'a']
Output: | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] | NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | zs_opt |
Definition: You are given a set of queries separated by '
', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.
Input: How do you clean polyester garden furniture ?
Best picture oscar 2001 ?
What is the name of the Russian space probe that visited haley 's comet ?
How can you seperate mixtures ?
Output: | Best picture oscar 2001 ? | NIv2 | task674_google_wellformed_query_sentence_generation | zs_opt |
Instructions: Evaluate the similarity between them and classify them into classes from 0-5 as follows:
0 : The two sentences are completely dissimilar.
1 : The two sentences are not equivalent, but are on the same topic.
2 : The two sentences are not equivalent, but share some details.
3 : The two sentences are roughly equivalent, but some important information differs/missing.
4 : The two sentences are mostly equivalent, but some unimportant details differ.
5 : The two sentences are completely equivalent, as they mean the same thing.
Input: Sentence 1: Israel's Peres urges return to peace talks Sentence 2: Israel's Peres calls for return to peace talks
Output: | 5 | NIv2 | task1347_glue_sts-b_similarity_classification | zs_opt |
In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.
Q: Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.
A: | Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue | NIv2 | task668_extreme_abstract_summarization | zs_opt |
In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
Let me give you an example: Who were the builders of the mosque in Herat with fire temples ?
The answer to this example can be: Ghurids
Here is why: This is a good example. Ghurids were the builders of the mosque in Herat with fire temples.
OK. solve this:
What company took over the station with the lowest UHF number ?
Answer: | Viacom | NIv2 | task344_hybridqa_answer_generation | fs_opt |
You are given an amazon food product review and its polarity (positive or negative). Your task is to answer "True" if the specified sentence and its polarity match; otherwise, answer "False".
Tastes like drinking a cherry pie. I purchased this for my mother's gout and she told me it works quickly. It's also supposed to help lower blood pressure. Speedy delivery. It's not 5 stars because of the high price.
Polarity: Negative
False
I bought this candy on a whim because I love pretty much all things coconut. I figured it would taste like a m&m's version of an almond joy minus the almonds, but was much disappointed. It tasted like an overly sweet waxy coconut body lotion, with a hint of chocolate and candy shell. UTTERLY DISGUSTING. Too late, i noticed on the ingredients list there was no coconut at all to be found--it's all artificial flavoring. I had to throw the bag away.
Polarity: Positive
False
Great value and much superior to what you find in stores. Makes a great snack or after dinner treat, but for those who are health conscious remember to keep it to a few pieces since they are covered in thin sugar. Try to keep the bag tightly sealed once you open them since the slowly begin to dry up. Will be ordering more soon :)
Polarity: Negative
| False
| NIv2 | task587_amazonfood_polarity_correction_classification | fs_opt |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding "Yes". Otherwise, respond "No". There are only two types of responses possible:"Yes" and "No".
Paragraph- Sent 1: It was hot that day.
Sent 2: The temperature on the wall of the backyard was showing something well over 100 F.
Sent 3: Meanwhile Tom, at home, was trying finish the remainder of carrots from last night, and packing for his trip to Chicago tomorrow.
Sent 4: As employees of the Art Museum, Tom and his older cousin often had to travel to Chicago. Question: What was the temperature outside, when Tom was eating carrots? Incorrect Answer: Far below 100 F.
Solution: Yes.
Why? This is a good incorrect answer, as the words corresponding to this answer appear in the the paragraph (at least partially). They are also related to the content of the question (temperature), but do not answer the question correctly. Someone will have to carefully read the paragraph to identify that these don't answer the question correctly. Therefore, this is labelled as "yes" and thus it is a good response.
New input: Paragraph- Sent 1: Fatty plays a somewhat lazy young man who disrupts his mother 's life by causing a fire by smoking in bed , then ruins laundry day by dropping it in the mud .
Sent 2: He has two loves of his life , the girl next door Lizzie and his dog Luke .
Sent 3: After showcasing his lack of talents helping his mother , he is able to save Luke from the dog catchers and express his love for Lizzie through a hole in the fence .
Sent 4: In the second reel , Fatty , Lizzie , mom and Luke go to the amusement park , where Fatty is first outwitted by a couple of sharks but then retrieves his losses by pointing a fake gun at them .
Sent 5: To extract revenge , they kidnap Lizzie with the help of the embittered dog catchers , and take her to an abandoned shack , where they tie her to a post with a gun attached to a timer pointed at her head .
Sent 6: Plucky pup Luke follows the crooks , and is able to warn Fatty in time to perform the last-minute rescue , with the help of the Keystone Cops .
Sent 7: In the closing shot Fatty , Lizzie and Luke embrace in a joint kiss .
Question: Who expresses his love for Lizzie through a hole in the fence?
Incorrect Answer: luke.
Solution: | No. | NIv2 | task057_multirc_classify_incorrect_answer | fs_opt |
Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].
Ex Input:
What is the sentiment of the following document towards the entity J. Christopher Giancarlo ? Speaking about blockchain systems broadly Chairman Giancarlo argued that the emerging technology will have a lasting impact on global financial markets.
Ex Output:
Neutral
Ex Input:
What is the sentiment of the following document towards the entity Trump Jr. ? Donald Trump Jr. will return to Capitol Hill Wednesday to talk to the Senate intelligence committee as part of its probe into Russian interference in the 2016 election.
Ex Output:
Positive
Ex Input:
What is the sentiment of the following document towards the entity Nikolas Cruz ? BREAKING: Spokesperson for white supremacist group Republic of Florida admitted to ADL that Nikolas Cruz alleged perpetrator of deadly Parkland school shooting was a member & trained with his group which seeks to create a âwhite ethnostate.â More info: [Link] â Jonathan Greenblatt (@JGreenblattADL) February 15 2018
Ex Output:
| Neutral
| NIv2 | task421_persent_sentence_sentiment_classification | fs_opt |
Q: Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.
Sentence: In a matter of 48 hours, Alexander II planned to release his plan for the duma to the Russian people.
Question: What did Alexander II do before releasing his plan?
Category: Event Ordering.
A: | Yes. | NIv2 | task019_mctaco_temporal_reasoning_category | zs_opt |
Detailed Instructions: In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
Q: What is the part-of-speech tag of the word "by" in the following question: When was the boat commanded by the oldest korvettenkapitän launched ?
A: | IN | NIv2 | task382_hybridqa_answer_generation | zs_opt |
Teacher: In this task, you are given a passage which has a question and the context. You have to generate an answer to the question based on the information present in the context.
Teacher: Now, understand the problem? If you are still confused, see the following example:
Context: Chronic rhinosinusitis (CRS) is a heterogeneous disease with an uncertain pathogenesis. Group 2 innate lymphoid cells (ILC2s) represent a recently discovered cell population which has been implicated in driving Th2 inflammation in CRS; however, their relationship with clinical disease characteristics has yet to be investigated. The aim of this study was to identify ILC2s in sinus mucosa in patients with CRS and controls and compare ILC2s across characteristics of disease. A cross-sectional study of patients with CRS undergoing endoscopic sinus surgery was conducted. Sinus mucosal biopsies were obtained during surgery and control tissue from patients undergoing pituitary tumour resection through transphenoidal approach. ILC2s were identified as CD45(+) Lin(-) CD127(+) CD4(-) CD8(-) CRTH2(CD294)(+) CD161(+) cells in single cell suspensions through flow cytometry. ILC2 frequencies, measured as a percentage of CD45(+) cells, were compared across CRS phenotype, endotype, inflammatory CRS subtype and other disease characteristics including blood eosinophils, serum IgE, asthma status and nasal symptom score. 35 patients (40% female, age 48 ± 17 years) including 13 with eosinophilic CRS (eCRS), 13 with non-eCRS and 9 controls were recruited. ILC2 frequencies were associated with the presence of nasal polyps (P = 0.002) as well as high tissue eosinophilia (P = 0.004) and eosinophil-dominant CRS (P = 0.001) (Mann-Whitney U). They were also associated with increased blood eosinophilia (P = 0.005). There were no significant associations found between ILC2s and serum total IgE and allergic disease. In the CRS with nasal polyps (CRSwNP) population, ILC2s were increased in patients with co-existing asthma (P = 0.03). ILC2s were also correlated with worsening nasal symptom score in CRS (P = 0.04).
Question: Are group 2 innate lymphoid cells ( ILC2s ) increased in chronic rhinosinusitis with nasal polyps or eosinophilia?
Solution: As ILC2s are elevated in patients with CRSwNP, they may drive nasal polyp formation in CRS. ILC2s are also linked with high tissue and blood eosinophilia and have a potential role in the activation and survival of eosinophils during the Th2 immune response. The association of innate lymphoid cells in CRS provides insights into its pathogenesis.
Reason: The output says that ILC2s are elevated in patients with CRSwNP and that they may drive nasal polyp formtion in CRS. The output also says that ILC2s are linked with blood eosinophilia and hence, it completely answers the question on the basis of the information in the context.
Now, solve this instance: Context: Aggressive periodontitis is characterized by rapid destruction of periodontal tissue caused by Aggregatibacter actinomycetemcomitans. Interleukin (IL)-1β is a proinflammatory cytokine, and its production is tightly regulated by inflammasome activation. Xylitol, an anticaries agent, is anti-inflammatory, but its effect on inflammasome activation has not been researched. This study investigates the effect of xylitol on inflammasome activation induced by A. actinomycetemcomitans.', 'The differentiated THP-1 macrophages were stimulated by A. actinomycetemcomitans with or without xylitol and the expressions of IL-1β and inflammasome components were detected by real time PCR, ELISA, confocal microscopy and Immunoblot analysis. The effects of xylitol on the adhesion and invasion of A. actinomycetemcomitans to cells were measured by viable cell count.', 'A. actinomycetemcomitans increased pro IL-1β synthesis and IL-1β secretion in a multiplicity of infection- and time-dependent manner. A. actinomycetemcomitans also stimulated caspase-1 activation. Among inflammasome components, apoptosis-associated speck-like protein containing a CARD (ASC) and absent in melanoma 2 (AIM2) proteins were upregulated by A. actinomycetemcomitans infection. When cells were pretreated with xylitol, proIL-1β and IL-1β production by A. actinomycetemcomitans infection was significantly decreased. Xylitol also inhibited ASC and AIM2 proteins and formation of ASC puncta. Furthermore, xylitol suppressed internalization of A. actinomycetemcomitans into differentiated THP-1 macrophages without affecting viability of A. actinomycetemcomitans within cells.\Question: Does aggregatibacter actinomycetemcomitans-Induced AIM2 Inflammasome Activation be Suppressed by Xylitol in Differentiated THP-1 Macrophages?
Student: | A. actinomycetemcomitans induced IL-1β production and AIM2 inflammasome activation. Xylitol inhibited these effects, possibly by suppressing internalization of A. actinomycetemcomitans into cells. Thus, this study proposes a mechanism for IL-1β production via inflammasome activation and discusses a possible use for xylitol in periodontal inflammation caused by A. actinomycetemcomitans. | NIv2 | task849_pubmedqa_answer_generation | fs_opt |
Definition: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.
Input: This man and Blatt name a method for inducing cognitive dissonance by asking questions and then letting the subject spontaneously formulate a response. He used the term "Hierarchic Integration" to describe one of his theories, which relies on a process of conflict resolution called "justice operation." This psychologist proposed a thought experiment in which a man breaks into adrug store to steal for his sick wife. His best-known work was criticized for only examining male subjects in the book In A Different Voice by Carol Gilligan. That work outlines a theory dividing development into three levels: pre-conventional, conventional, and post-conventional. For 10 points, name this psychologist who outlined a six stage theory of moral development.
Output: | Social Science | NIv2 | task521_trivia_question_classification | zs_opt |
Given the task definition and input, reply with output. You are given a math word problem and you are supposed to apply multiple mathematical operators like addition, subtraction, multiplication or division on the numbers embedded in the text to answer the following question and then only report the final numerical answer.
There are 43 pencils in the drawer and 19 pencils on the desk . Dan placed 16 pencils on the desk . How many pencils are now there in total ?
| 78 | NIv2 | task867_mawps_multiop_question_answering | zs_opt |
Q: You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with "Description", "Entity", "Abbreviation", "Person", "Quantity", and "Location".
What is the price for tuberculosis drugs ?
A: | Quantity | NIv2 | task1289_trec_classification | zs_opt |
In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.
Input: Consider Input: Title: The Locked Car. Sentence 1: Adam paid the locksmith. Sentence 2: He called a locksmith. Sentence 3: The locksmith unlocked Adam's car. Sentence 4: Adam locked his keys in his car. Sentence 5: He was more careful when locking his car to check for his keys.
Output: 41
Input: Consider Input: Title: That Says A Lot. Sentence 1: I had to tell my boyfriend that the cat can't sleep with us anymore. Sentence 2: Today I found out I'm highly allergic to cats. Sentence 3: At about 1:30 this morning, I felt him get out of bed. Sentence 4: I asked him where he was going so late. Sentence 5: He said to sleep in the living room because the cat is sad.
Output: 21
Input: Consider Input: Title: Nap Time. Sentence 1: My 2 year old daughter hates naps. Sentence 2: Today she hid under the bed. Sentence 3: Every day she tries to trick me into letting her stay awake. Sentence 4: I let her stay under there. Sentence 5: She ended up taking a nap under the bed instead!
| Output: 32
| NIv2 | task218_rocstories_swap_order_answer_generation | fs_opt |
Detailed Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Problem:Head: PersonX answers PersonY's letter<sep>Tail: to invite PersonY
Solution: | No | NIv2 | task1212_atomic_classification_hasproperty | zs_opt |
Detailed Instructions: In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.
Q: Simmer cherry juice in a saucepan over medium-high heat, stirring frequently, until the juice is reduced to about 1/2 cup in volume, about 20 to 25 minutes. Remove from heat and pour into a bowl to cool to room temperature., Pour reduced cherry juice, red wine vinegar, and white vinegar together in a blender; add mustard, chile-garlic sauce, salt, and pepper. Blend for 30 seconds. Add a drop of grapeseed oil and blend another 30 seconds. Pour remaining oil into the blender; blend for 2 minutes.
A: | cherry juice, red wine vinegar, white vinegar, mustard, chile-garlic sauce, salt, grapeseed oil | NIv2 | task571_recipe_nlg_ner_generation | zs_opt |
In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.
Example input: For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.
Example output: Michel Temer: Brazil's arrested former president
Example explanation: The output is a relevant title for the given passage as it highlights the main crux of the given text.
Q: Rihanna says that she she still loves ex-boyfriend Chris Brown despite him attacking her in 2009.
A: | Rihanna 'still loves' Chris Brown after assault | NIv2 | task1358_xlsum_title_generation | fs_opt |
Detailed Instructions: In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.
See one example below:
Problem: [['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]
Solution: The team whose nickname is red raiders is located in the _______
Explanation: This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa.
Problem: [['Cotto', 'eatType', 'coffee shop'], ['Cotto', 'priceRange', 'moderate'], ['Cotto', 'customer rating', '3 out of 5'], ['Cotto', 'area', 'city centre'], ['Cotto', 'near', 'The Portland Arms']]
Solution: | Situated near The Portland Arms on the riverfront, north of the City centre, the 3-star '_____' coffee shop serves a range of moderately-priced fast foods. | NIv2 | task1407_dart_question_generation | fs_opt |
This is a paraphrasing task. In this task, you're given a sentence and your task is to generate another sentence which express same meaning as the input using different words.
yes , but distantly distantly yes , distance you 've transformed your passion into a hobby you shouldnt treat your talent that way ! | yes , but remotely true yes , you 've turned your passion into a hobby . | NIv2 | task177_para-nmt_paraphrasing | zs_opt |
Given the task definition and input, reply with output. Given a sentence, an entity and its sentiment towards the entity, verify if it is the correct sentiment towards the entity. Answer should be yes or no. Note that URLs in the text have been replaced with [Link].
Verify if the sentiment of the following document towards the entity Darren Drake is Positive . Last Tuesday Drake was on a CitiBike listening to an audio book when he was hit by 29-year-old Sayfullo Saipov who drove a rented Home Depot truck through the lower Manhattan bike lane.
| yes | NIv2 | task422_persent_sentence_sentiment_verification | zs_opt |
In this task, you will be presented with a question in Persian. Based on the knowledge you need to answer the question, classify the question into "math_and_logic", "literature", or "common_knowledge".
Q: متضاد کلمات مورد سؤال چیست؟ سترون
A: literature
****
Q: همه موارد از دیدگاه تاریخ ادبیات کاملا درست است؛ بهجز:
A: literature
****
Q: کدام کتاب اثر ویکتور هوگو نیست؟
A: | literature
****
| NIv2 | task474_parsinlu_mc_classification | fs_opt |
In this task, you are given a question and an answer. Answer "Yes" if the given answer correctly answers the question, otherwise answer "No".
Example: what latitude is tropic of cancer, Answer: It currently (Year 2013) lies at 23° 26′ 15.143′′ north of the Equator.
Example solution: Yes
Example explanation: This is a good example, and the given answer correctly answers the question.
Problem: how old is the singer bob seger, Answer: As a locally successful Detroit-area artist, he performed and recorded as Bob Seger and the Last Heard and Bob Seger System throughout the 1960s.
| Solution: No | NIv2 | task1294_wiki_qa_answer_verification | fs_opt |
In this task, you need to count the number of nouns/verbs in the given sentence.
--------
Question: Sentence: 'A red train engine coming into a station'. Count the number of nouns in this sentence.
Answer: 3
Question: Sentence: 'a bathroom view of a tiolet, bathtub sitting on a tiled floor'. Count the number of nouns in this sentence.
Answer: 5
Question: Sentence: 'A closeup of a pizza with whole tomato slices'. Count the number of nouns in this sentence.
Answer: | 4
| NIv2 | task155_count_nouns_verbs | fs_opt |
Detailed Instructions: In this task, you are given a short passage that conveys stereotype or anti-stereotype about a specific target. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into four types of stereotype or anti-stereotype: gender, profession, race, and religion.
Problem:Passage: Did you know that a mathematician lives on Sally's street? She wears the cutest dresses and likes to go out dancing.
Solution: | Profession | NIv2 | task280_stereoset_classification_stereotype_type | zs_opt |
TASK DEFINITION: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
PROBLEM: What is the continues to place of the line that is displayed in the color purple on station placards , the formal subway map , and internal route maps in R188 cars ?
SOLUTION: Queens
PROBLEM: When was the city where the oldest championship record was set founded ?
SOLUTION: 1812
PROBLEM: What company took over the station with the lowest UHF number ?
SOLUTION: | Viacom
| NIv2 | task344_hybridqa_answer_generation | fs_opt |
In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form " A >Causes> B". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).
One example: story: Our neighbors down the hall had a very noisy party. One of the guests passed out in front of my door. When I asked him to leave he swore at me. I called the police. The guest left before the police came.
selected sentence: When I asked him to leave he swore at me.
Solution is here: I ask him to leave >Causes> He feel(s) angered
Explanation: The emotion caused by the sentence can be anger or being upset, as the person involved swears. This is a good answer.
Now, solve this: story: David had a bad toothache. He made an appointment with the dentist. The next week the dentist had to pull his tooth. David went home very sore to recover. The next day David felt much better without the pain.
selected sentence: The next week the dentist had to pull his tooth.
Solution: | The dentist has to pull his tooth >Causes> David feel(s) pained | NIv2 | task749_glucose_reverse_cause_emotion_detection | fs_opt |
Detailed Instructions: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e. tagset of this corpus is 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, 'PART': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.
Q: Sentence: The Gu'ud family {{ even }} accepted to be offered the seat of Al - Anbar governor some months back .
Word: even
A: | ADV | NIv2 | task583_udeps_eng_coarse_pos_tagging | zs_opt |
Part 1. Definition
In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
Part 2. Example
#RPDR FUCKING FARRAH MOAN, HAVE YOU NEVER WATCHED THIS SHOW. WHEN YOU GET THE CALL, TAKE A LESSON.
Answer: Yes
Explanation: (Correct Answer) This post is aggressive and berates a person for not having watched a show. Therefore the correct answer is 1/Potentially Offensive.
Part 3. Exercise
RT @HeidiL_RN: Fuck Islam you pigfucking trash troll. @ItsJustMe7o7 @MzKeriEvans @ctbauza
Answer: | Yes | NIv2 | task609_sbic_potentially_offense_binary_classification | fs_opt |
In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding "Yes". Otherwise, respond "No". There are only two types of responses possible:"Yes" and "No".
Paragraph- Sent 1: Sam Farragut is a sociopathic business executive in Southern California who forces a team of advertising agency employees to embark on a dangerous dirtbike trip to the Baja California desert in order to compete for his business .
Sent 2: The men are Warren Summerfield , a suicidal middle-aged ad executive who has been fired from the agency ; the straightlaced Paul McIlvain who is inattentive to his wife , and brash art designer Maxon who feels suddenly trapped after his girlfriend announces she is pregnant .
Sent 3: There are numerous long sequences of motorcycle riding on desert backroads .
Sent 4: Summerfield has been having an affair with McIlvian 's wife .
Sent 5: He has not told his wife that he was fired and is simply serving out his tenure at the agency while looking for a new position .
Sent 6: His wife is actually aware of the affair .
Sent 7: Farragut convinces the ad men to make the motorcycle journey on the pretext of looking for a location to shoot a commercial .
Sent 8: In reality , Farragut is reckless and looking to involve the men in spontaneous edgy adventure of his own manipulation .
Sent 9: After they leave , McIlvain 's wife suspects that Summerfield is planning to kill himself for the insurance money , but she can not convince Summerfield 's wife to instigate a search .
Sent 10: The four men travel deeper into Mexico on isolated dirt roads .
Sent 11: At one point Summerfield contemplates plunging off a cliff .
Sent 12: After being humiliated by a young American couple in a Baja bar , Farragut tracks them down on the beach while accompanied by Maxon .
Question: Who is Summerfield having an affair with and does his wife know that he is having an affair?
Incorrect Answer: Maxon.
Yes.
Paragraph- Sent 1: The opening shot of the movie shows Kunti praying for Lord Krishna 's protection for the Pandavas .
Sent 2: Lord Krishna consoles Kunti and promises to ever protect the Pandavas and guide them through troubles and problems that may occur in life .
Sent 3: The sons of Pandu and Dhritarashtra progeny break into an argument .
Sent 4: When Duryodhana insults the Pandavas as `` dependents '' , Bheema counters by saying that , the Kauravas are the progeny of a widow .
Sent 5: Duryodhana asks Veda Vyasa for an explanation .
Sent 6: He is then told that , since his mother , Gandhari had an astrological defect , she is first married of to a goat and then married to his father .
Sent 7: Duryodhana gains animosity towards the kingdom of Gandhara where the king , the father of his mother Gandhari , rules .
Sent 8: He attacks Gandhara and lays waste of the whole kingdom .
Sent 9: He them imprisons the royal family in his prison .
Sent 10: He gives them only one rice grain per prisoner .
Sent 11: The king of Gandhara then stops everyone from grabbing the little food that is provided .
Sent 12: He says that instead of everyone dying , they could keep at least one of their princes alive .
Sent 13: He chooses Sakuni to be alive .
Sent 14: Sakuni takes an oath that he will do everything he can to destroy the entire Kaurava clan .
Sent 15: He makes magic dice from his father 's spinal cord .
Sent 16: The magic dice show exactly the number that he would want .
Sent 17: Duryodhana takes pity on the lone prisoner , Sakuni after the rest of the Gandhara royal family dies in prison out of starvation .
Sent 18: Sakuni joins the evil of coterie of Duryodhana , Karna and Dushyasana .
Question: Who attacked the kingdom of Gandhara?
Incorrect Answer: c.
Yes.
Paragraph- Sent 1: Fatty plays a somewhat lazy young man who disrupts his mother 's life by causing a fire by smoking in bed , then ruins laundry day by dropping it in the mud .
Sent 2: He has two loves of his life , the girl next door Lizzie and his dog Luke .
Sent 3: After showcasing his lack of talents helping his mother , he is able to save Luke from the dog catchers and express his love for Lizzie through a hole in the fence .
Sent 4: In the second reel , Fatty , Lizzie , mom and Luke go to the amusement park , where Fatty is first outwitted by a couple of sharks but then retrieves his losses by pointing a fake gun at them .
Sent 5: To extract revenge , they kidnap Lizzie with the help of the embittered dog catchers , and take her to an abandoned shack , where they tie her to a post with a gun attached to a timer pointed at her head .
Sent 6: Plucky pup Luke follows the crooks , and is able to warn Fatty in time to perform the last-minute rescue , with the help of the Keystone Cops .
Sent 7: In the closing shot Fatty , Lizzie and Luke embrace in a joint kiss .
Question: Who expresses his love for Lizzie through a hole in the fence?
Incorrect Answer: luke.
| No.
| NIv2 | task057_multirc_classify_incorrect_answer | fs_opt |
You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.
Let me give you an example: Sentence1:i need a place to dine in the center thats expensive Sentence2: I have several options for you; do you prefer African, Asian, or British food? Sentence3: Any sort of food would be fine, as long as it is a bit expensive. Could I get the phone number for your recommendation?Question: Who has spoken the sentence 2? (A) User (B) System
The answer to this example can be: Answer: (A) User
Here is why: The sentence 1 is said by a user because the intent of it says that the information has to be gathered from the system
OK. solve this:
Sentence1: Booking was successful. The table will be reserved for 15 minutes. Reference number is : IMSY2GMJ . Is there anything else I can do for you today? Sentence2: Two people at 11:15 for 2 people. Sentence3: What day would you like to book your reservation? Sentence4: No, thank you Sentence5: Have a great day! Sentence6: I found one for you called restaurant alimentum. Would you like me to book it for you? Sentence7: Yes! Sentence8: I am looking for a local restaurant in the south that offers modern European cuisine Sentence9: For which day shall I book the table? Sentence10: Tuesday, please. Question: Who has spoken the sentence 8? (A) User (B) System
Answer: | Answer: (A) User | NIv2 | task638_multi_woz_classification | fs_opt |
You are given a sentence in English. Your job is to translate the English sentence into Arabic.
What does that even mean? | ما الذي يعنيه ذلك ؟ | NIv2 | task1220_ted_translation_en_ar | zs_opt |
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
One example is below.
Q: Head: PersonX plays a song<sep>Tail: to hear music.
A: Yes
Rationale: This is a good example. PersonX plays a song because PersonX wanted to hear music.
Q: Head: PersonX offer PersonY a position<sep>Tail: some help
A: | Yes | NIv2 | task1201_atomic_classification_xintent | fs_opt |
In this task, you are given a passage which has a question and the context. You have to generate an answer to the question based on the information present in the context.
Input: Consider Input: Context: The bradycardic agent zatebradine (UL-FS 49) reduces heart rate without negative inotropic or proarrhythmic effects. The aim was to experimentally characterize the influence of zatebradine on arterial baroreflex sensitivity (BRS) and heart rate variability (HRV) which are generally considered as estimates of vagal activity and have prognostic value in patients after myocardial infarction (MI).', 'Conscious rats were studied 3 days after left coronary artery ligation or sham-operation (SH). BRS was determined by linear regression analysis of RR-interval and mean arterial pressure changes evoked by intravenous (i.v.) injections of methoxamine and nitroprusside. HRV at rest was calculated from high-resolution electrocardiogram-recordings.', 'In MI-rats heart rate was similar to SH-rats, mean arterial pressure was lower and both BRS and HRV were markedly reduced. Zatebradine (0.5 mg/kg i.v.) reduced heart rate in MI-rats from 400 +/- 15 to 350 +/- 19 and in SH-rats from 390 +/- 19 to 324 +/- 6 beats/min without changing mean arterial pressure. Both BRS and HRV were restored in MI- and further increased in SH-rats by the drug. Effects of 0.05, 0.5 and 5 mg/kg zatebradine revealed a dose-dependency of heart rate reduction. The lowest dose enhanced reflex bradycardia despite little effect on heart rate and lack of effect on both reflex tachycardia and HRV.\Question: Does the bradycardic agent zatebradine enhance baroreflex sensitivity and heart rate variability in rats early after myocardial infarction?
Output: Both BRS and HRV are reduced in rats early after MI, indicating a depressed reflex and tonic vagal activity. Treatment with zatebradine enhances both BRS and HRV. These data suggest that the drug has both peripheral and central effects, leading to an increase of vagal control of heart rate.
Input: Consider Input: Context: Linitis plastica-type gastric carcinoma remains a disease with poor prognosis despite an aggressive surgical approach. Although a prominent pattern of disease failure is peritoneal carcinomatosis, some patients experience rapid disease progression without signs of the peritoneal disease.', 'Clinicopathologic data from 178 patients with linitis plastica-type gastric cancer operated on between 1991 and 2000 were analyzed. Survival stratified by curability of surgery, pN stage, and patterns of failure were evaluated by using the Kaplan-Meier method, and chi(2) test was used to evaluate correlation between the number of metastatic lymph nodes in terms of pN categories and the incidence of various patterns of metastasis and recurrence. Cox regression hazard model was used to identify independent prognostic factors.', 'R0 resection was performed only among 82 patients (46% of those who underwent laparotomy). Node metastasis was frequent with only 22 patients classified as pN0. Peritoneal carcinomatosis was observed in 131 patients and was the commonest pattern of recurrence. Bone metastasis, found in 13 patients, was associated with poor outcome, and its incidence was significantly correlated with the number of metastatic nodes. pT4 status and pN3 status were identified as significant independent prognostic determinants.\Question: Is the number of metastatic lymph nodes a significant risk factor for bone metastasis and poor outcome after surgery for linitis plastica-type gastric carcinoma?
Output: Treatment strategy for the linitis plastica should in general combine surgery with aggressive treatment directed toward peritoneal disease. However, patients with >16 metastatic nodes more often are associated with bone metastasis than those with modest nodal involvement and suffer from poor prognosis.
Input: Consider Input: Context: Aggressive periodontitis is characterized by rapid destruction of periodontal tissue caused by Aggregatibacter actinomycetemcomitans. Interleukin (IL)-1β is a proinflammatory cytokine, and its production is tightly regulated by inflammasome activation. Xylitol, an anticaries agent, is anti-inflammatory, but its effect on inflammasome activation has not been researched. This study investigates the effect of xylitol on inflammasome activation induced by A. actinomycetemcomitans.', 'The differentiated THP-1 macrophages were stimulated by A. actinomycetemcomitans with or without xylitol and the expressions of IL-1β and inflammasome components were detected by real time PCR, ELISA, confocal microscopy and Immunoblot analysis. The effects of xylitol on the adhesion and invasion of A. actinomycetemcomitans to cells were measured by viable cell count.', 'A. actinomycetemcomitans increased pro IL-1β synthesis and IL-1β secretion in a multiplicity of infection- and time-dependent manner. A. actinomycetemcomitans also stimulated caspase-1 activation. Among inflammasome components, apoptosis-associated speck-like protein containing a CARD (ASC) and absent in melanoma 2 (AIM2) proteins were upregulated by A. actinomycetemcomitans infection. When cells were pretreated with xylitol, proIL-1β and IL-1β production by A. actinomycetemcomitans infection was significantly decreased. Xylitol also inhibited ASC and AIM2 proteins and formation of ASC puncta. Furthermore, xylitol suppressed internalization of A. actinomycetemcomitans into differentiated THP-1 macrophages without affecting viability of A. actinomycetemcomitans within cells.\Question: Does aggregatibacter actinomycetemcomitans-Induced AIM2 Inflammasome Activation be Suppressed by Xylitol in Differentiated THP-1 Macrophages?
| Output: A. actinomycetemcomitans induced IL-1β production and AIM2 inflammasome activation. Xylitol inhibited these effects, possibly by suppressing internalization of A. actinomycetemcomitans into cells. Thus, this study proposes a mechanism for IL-1β production via inflammasome activation and discusses a possible use for xylitol in periodontal inflammation caused by A. actinomycetemcomitans.
| NIv2 | task849_pubmedqa_answer_generation | fs_opt |
In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.
Example Input: Urgent safety guidance for wagons carrying dangerous goods has been issued after a derailment in which 330,000 litres of diesel was spilled.
Example Output: Llangennech derailment: Safety guidance for dangerous goods
Example Input: More than £2m of government funding will go towards moving two GP surgeries in Shropshire into a nearby empty hospital ward, health bosses say.
Example Output: £2m 'to relocate two Whitchurch GP surgeries'
Example Input: Rihanna says that she she still loves ex-boyfriend Chris Brown despite him attacking her in 2009.
Example Output: | Rihanna 'still loves' Chris Brown after assault
| NIv2 | task1358_xlsum_title_generation | fs_opt |
In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.
Q: [['The Waterman', 'eatType', 'restaurant'], ['The Waterman', 'food', 'Chinese'], ['The Waterman', 'priceRange', 'less than £20'], ['The Waterman', 'customer rating', 'low'], ['The Waterman', 'area', 'riverside'], ['The Waterman', 'familyFriendly', 'no']]
A: Chinese _____ _____ is located in the riverside area and has a low customer rating. It has dishes costing less than 20 pounds and is not family friendly.
****
Q: [['Allen Park', 'CITY', 'Antrim'], ['Allen Park', 'HOME_TEAM', 'Chimney Corner']]
A: _____ in Antrim is home to the Chimney Corner football club.
****
Q: [['Cotto', 'eatType', 'coffee shop'], ['Cotto', 'priceRange', 'moderate'], ['Cotto', 'customer rating', '3 out of 5'], ['Cotto', 'area', 'city centre'], ['Cotto', 'near', 'The Portland Arms']]
A: | Situated near The Portland Arms on the riverfront, north of the City centre, the 3-star '_____' coffee shop serves a range of moderately-priced fast foods.
****
| NIv2 | task1407_dart_question_generation | fs_opt |
In this task, you are given a question and an answer. Answer "Yes" if the given answer correctly answers the question, otherwise answer "No".
[Q]: what is the name of the wizard of oz, Answer: The Wizard of Oz, known during his reign as The Great and Powerful Oz, is the epithet of Oscar Zoroaster Phadrig Isaac Norman Henkel Emmannuel Ambroise Diggs, a fictional character in the Land of Oz , created by American author L. Frank Baum .
[A]: Yes
[Q]: how many vehicles are registered in the us, Answer: Overall, there were an estimated 254.4 million registered passenger vehicles in the United States according to a 2007 DOT study.
[A]: Yes
[Q]: how old is the singer bob seger, Answer: As a locally successful Detroit-area artist, he performed and recorded as Bob Seger and the Last Heard and Bob Seger System throughout the 1960s.
[A]: | No
| NIv2 | task1294_wiki_qa_answer_verification | fs_opt |
You will be given a definition of a task first, then some input of the task.
Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.
What wasn't Chief Hendrick er uh William Johnson's role in British military?
Output: | What wasn't William Johnson's role in British military? | NIv2 | task1195_disflqa_disfluent_to_fluent_conversion | zs_opt |
In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form " A >Causes> B". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).
[EX Q]: story: Katelyn was sitting with her toddler. Their favorite song came on. The toddler wanted to sing. Katelyn began singing with him. The toddler loved it.
selected sentence: Katelyn began singing with him.
[EX A]: Katelyn sings with him >Causes> He feel(s) happy
[EX Q]: story: I turned on the television. My dog was sitting on the sofa. He started to watch the television. The dog show came on the television. My dog started barking at the dogs on television.
selected sentence: He started to watch the television.
[EX A]: My dog watched TV >Causes> My dog feel(s) included
[EX Q]: story: David had a bad toothache. He made an appointment with the dentist. The next week the dentist had to pull his tooth. David went home very sore to recover. The next day David felt much better without the pain.
selected sentence: The next week the dentist had to pull his tooth.
[EX A]: | The dentist has to pull his tooth >Causes> David feel(s) pained
| NIv2 | task749_glucose_reverse_cause_emotion_detection | fs_opt |
Definition: In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.
Input: Query: What are specific dangers of asbestos?
Clarification: do you want stores selling elliptical trainer
Output: | No | NIv2 | task227_clariq_classification | zs_opt |
Given the task definition, example input & output, solve the new input case.
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Example: ['hey', 'everybody', 'ivan', 'from', 'weights', 'and', 'biases', 'here', 'in', 'this', 'video', "i'd"]
Output: ['CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF']
This sentence is a good example since the input stream is a grammatically incorrect statement and the output labels correctly classify the words that were incorrect.
New input case for you: ['over', '2,000', 'years', 'ago', 'Euclid', 'showed', 'every', 'number', 'has', 'exactly', 'one', 'prime', 'factorization', 'which', 'we', 'can', 'think', 'of', 'as', 'a', 'secret', 'key', 'it', 'turns', 'out', 'that', 'prime', 'factorization', 'is', 'a', 'fundamentally', 'hard', 'problem', "let's", 'clarify', 'what', 'we', 'mean', 'by', 'easy', 'and', 'hard', 'by', 'introducing', "what's", 'called', 'time', 'complexity', 'we', 'have', 'all', 'multiplied', 'numbers', 'before', 'and', 'each', 'of', 'us', 'has', 'our', 'own', 'rules', 'for', 'doing', 'so', 'in', 'order', 'to', 'speed', 'things', 'up', 'if', 'we', 'program', 'a', 'computer', 'to', 'multiply', 'numbers', 'it', 'can', 'do', 'so', 'much', 'faster', 'than', 'any', 'human', 'can', 'here', 'is', 'a', 'graph', 'that', 'shows', 'the', 'time', 'required', 'for', 'a']
Output: | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] | NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | fs_opt |
Teacher: You are given a set of queries separated by '
', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.
Teacher: Now, understand the problem? If you are still confused, see the following example:
How many miles is 43560 ?
What is the national currency of Albania ?
What is the status of the draft today in US ?
Where is the oil plug in a 2004 Harley ?
Solution: How many miles is 43560 ?
Reason: The output is from the list of given queries and it is not well structured and has grammatical errors when compared to other queries
Now, solve this instance: How do you clean polyester garden furniture ?
Best picture oscar 2001 ?
What is the name of the Russian space probe that visited haley 's comet ?
How can you seperate mixtures ?
Student: | Best picture oscar 2001 ? | NIv2 | task674_google_wellformed_query_sentence_generation | fs_opt |
Evaluate the similarity between them and classify them into classes from 0-5 as follows:
0 : The two sentences are completely dissimilar.
1 : The two sentences are not equivalent, but are on the same topic.
2 : The two sentences are not equivalent, but share some details.
3 : The two sentences are roughly equivalent, but some important information differs/missing.
4 : The two sentences are mostly equivalent, but some unimportant details differ.
5 : The two sentences are completely equivalent, as they mean the same thing.
Example input: Sentence 1: A plane is taking off. Sentence 2: An air plane is taking off.
Example output: 5
Example explanation: Here both statements are talking about the same thing hence it will be classified as a 5.
Q: Sentence 1: Israel's Peres urges return to peace talks Sentence 2: Israel's Peres calls for return to peace talks
A: | 5 | NIv2 | task1347_glue_sts-b_similarity_classification | fs_opt |
Instructions: You are given a short paragraph, a question and two choices to answer from. Choose the correct answer based on the paragraph and write the answer(not the key).
Input: Paragraph: Objects with greater mass have greater inertia.
Question: When something is very lightweight what does it need to move?
Choices: A)more inertia
B)less inertia
Output: | less inertia | NIv2 | task1731_quartz_question_answering | zs_opt |
In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
--------
Question: Hell no it was mad niggas tryna talk to me today at work 😭😭🤦🏽♀️
Answer: Yes
Question: All these bitches & niggas be Trippin offa what type of relationship me & duddy got like we not fuccing no more & we not dating.
Answer: Yes
Question: RT @HeidiL_RN: Fuck Islam you pigfucking trash troll. @ItsJustMe7o7 @MzKeriEvans @ctbauza
Answer: | Yes
| NIv2 | task609_sbic_potentially_offense_binary_classification | fs_opt |
Detailed Instructions: In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.
See one example below:
Problem: Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in existing GPUs. MPT is typically used in combination with a technique called loss scaling, that works by scaling up the loss value up before the start of backpropagation in order to minimize the impact of numerical underflow on training. Unfortunately, existing methods make this loss scale value a hyperparameter that needs to be tuned per-model, and a single scale cannot be adapted to different layers at different training stages. We introduce a loss scaling-based training method called adaptive loss scaling that makes MPT easier and more practical to use, by removing the need to tune a model-specific loss scale hyperparameter. We achieve this by introducing layer-wise loss scale values which are automatically computed during training to deal with underflow more effectively than existing methods. We present experimental results on a variety of networks and tasks that show our approach can shorten the time to convergence and improve accuracy, compared with using the existing state-of-the-art MPT and single-precision floating point.
Solution: We devise adaptive loss scaling to improve mixed precision training that surpass the state-of-the-art results.
Explanation: The abstract focusses on designing an adaptive loss scaling method, hence the generated output is correct.
Problem: Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.
Solution: | Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue | NIv2 | task668_extreme_abstract_summarization | fs_opt |
TASK DEFINITION: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.
PROBLEM: Sentence1: I would prefer one of the expensive places. Need to impress my guests, you know? Sentence2: I see one moderately priced Indian restaurant in that area, and several expensive ones. Do you have a preference? Sentence3: Actually, I would like to book the hotel for 6 people for 4 nights starting on Sunday. Sentence4: I want an expensive place to stay in the west side. Sentence5: Okay, the phone number is 01480446000 for your convenience. Is there anything else I can help you with? Sentence6: There are three expensive Indian Restaurants in that area. Can I recommend Tandoori Palace? Sentence7: Thank you, you have a good day! Sentence8: I don't really need internet, but that sounds like everything else I want. Yes, I'd like you to book it. Sentence9: Yes, is 3 nights possible? Could I also please have a reference number? Sentence10: I was not able to reserve a table for you at that time. Is there a different day or time slot that you would like? Sentence11: Booking was not possible. Would you like to try a shorter stay, fewer rooms, or another day? Sentence12: Great! I have a table for 6 people at 11:30 onSundar at Tandoori Palace, Reference Number 3BMGPAN3 . Is there anything else I can do for you? Sentence13: I will hold off on the booking today I think I have all I need Sentence14: No thank you, that is all I needed! Sentence15: Thank you. I would like to make reservations for my party to have dinner one night near the hotel. We would like to go to a restaurant that serves Indian food, if possible. Sentence16: Great, the booking was successful. Your reference number is HJHE475H . Is there anything else I can help you with? Sentence17: OK, what is your arrival date, number of nights, and number of people in your party? Sentence18: Yes, that sounds good. Please book it for the same 6 people at 12:30 on Sunday. Sentence19: The Huntingdon Marriott Hotel is an expensive, 4-star hotel in the west that offers free internet and parking. Would you like me to book this for you? Sentence20: Yes, how about 11:30 instead? Please send reference number for the booking. Question: Who has spoken the sentence 1? (A) User (B) System
SOLUTION: Answer: (B) System
PROBLEM: Sentence1: What is your departure point? Sentence2: What time do you need to leave by? Sentence3: I am looking for a train to cambridge. I would like something on sunday to arrive by 18:30 Sentence4: I just want to get there at or shortly before 18:30. Sentence5: I'd like to recommend whipple museum of the history of science, at free school lane. Admission is free. Sentence6: Yes it is their full address and the postcode is cb23rh and their telephone number is 01223330906. May I help you with anything else today? Sentence7: Thank you. That is all that I need. Sentence8: i place want a place to go in the centre Sentence9: I found the perfect train! TR7771 will get you there at 18:24. Would you like me to book this for you? Sentence10: Ok, your booking is complete for 6 people. The cost is 79.19 GBP, payable at the station. The reference number is 8W0OSFM6 . Sentence11: I would like a museum in the centre please. Sentence12: What are you into? Do you like theatre? Museums? We have plenty of attractions in the centre and if you tell me what you enjoy I can recommend one Sentence13: My departure will be from Cambridge. Sentence14: Okay. Glad I could be of help. Sentence15: Is that the full address for the museum? Free School Lane? Sentence16: I need to go to Peterborough. Sentence17: Yes, please book me for 6 people. My birdwatching club is taking a trip together. Sentence18: And what is your destination city? Question: Who has spoken the sentence 6? (A) User (B) System
SOLUTION: Answer: (A) User
PROBLEM: Sentence1: Booking was successful. The table will be reserved for 15 minutes. Reference number is : IMSY2GMJ . Is there anything else I can do for you today? Sentence2: Two people at 11:15 for 2 people. Sentence3: What day would you like to book your reservation? Sentence4: No, thank you Sentence5: Have a great day! Sentence6: I found one for you called restaurant alimentum. Would you like me to book it for you? Sentence7: Yes! Sentence8: I am looking for a local restaurant in the south that offers modern European cuisine Sentence9: For which day shall I book the table? Sentence10: Tuesday, please. Question: Who has spoken the sentence 8? (A) User (B) System
SOLUTION: | Answer: (A) User
| NIv2 | task638_multi_woz_classification | fs_opt |
instruction:
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
question:
Head: PersonX plays PersonX's best<sep>Tail: to do well
answer:
Yes
question:
Head: PersonX affords every ___<sep>Tail: to spoil their fiance
answer:
No
question:
Head: PersonX offer PersonY a position<sep>Tail: some help
answer:
| Yes
| NIv2 | task1201_atomic_classification_xintent | fs_opt |
Given the task definition and input, reply with output. In this task you are given a tweet that contains some form of irony. You must classify the type of irony the tweet has. Label the tweets ("polarity","situational","other") based on the irony they have. Situational irony happens when a situation fails to meet some expectations, Label these instances as "situational". polarity irony happens when irony is achieved by inverting the intended sentence, Label these instances as "polarity". There are other kinds of ironies that are neither polarity nor situational, Label these instances as "other". Note that URLs in the text have been replaced with [Link].
@drapermark37 @susanbnj We must be tolerant and embrace the peaceful Islamic faith, Muslims are our peaceful brothers
| polarity | NIv2 | task387_semeval_2018_task3_irony_classification | zs_opt |
Part 1. Definition
Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.
Part 2. Example
Sentence: Jack played basketball after school, after which he was very tired.
Question: How long did Jack play basketball?
Category: Event Duration.
Answer: Yes.
Explanation: The question asks about the duration of playing basketball, therefore it's a "event duration" question.
Part 3. Exercise
Sentence: In a matter of 48 hours, Alexander II planned to release his plan for the duma to the Russian people.
Question: What did Alexander II do before releasing his plan?
Category: Event Ordering.
Answer: | Yes. | NIv2 | task019_mctaco_temporal_reasoning_category | fs_opt |
Detailed Instructions: Given a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.
Problem:Velma Kelly and Billy Flynn are two of the leading characters in which 2002 musical?
Solution: | film | NIv2 | task900_freebase_qa_category_classification | zs_opt |
In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
One example is below.
Q: What is the part-of-speech tag of the word "the" in the following question: Who were the builders of the mosque in Herat with fire temples ?
A: DT
Rationale: This is a good example. POS tag of "the" is DT.
Q: What is the part-of-speech tag of the word "by" in the following question: When was the boat commanded by the oldest korvettenkapitän launched ?
A: | IN | NIv2 | task382_hybridqa_answer_generation | fs_opt |
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Ex Input:
['when', 'you', 'ask', 'composers', 'who', 'their', 'favorite', 'composer', 'is', 'you', 'get', 'unusual', 'answers', 'regarde', 'Strauss', 'for', 'example', 'who', 'wrote', 'Elektra', 'and', 'Rosenkavalier', 'and', '', 'great', 'tone', 'poems', '-', 'Lauren', 'Spiegel', 'xerath', 'rooster', 'his', 'favorite', 'composer', 'was', 'Mozart', 'Tchaikovsky', 'this', 'great', 'Romantic', 'who', 'wrote', 'music', 'that', 'was', 'so', 'passionate', 'and', 'so', 'full', 'of', 'drama', 'his', 'favorite', 'composer', 'was', 'Mozart', 'you', "wouldn't", 'think', 'that', 'and', 'they', 'used', 'them', 'a', 'lot', 'of', 'miss', 'Strauss', 'for', 'example', 'conducted', 'Mozart', 'a', 'lot', 'Tchaikovsky', 'actually', 'wrote', 'a', 'suite', 'called', 'more', 'Tatiana', 'where', 'he', 'took', 'Mozart', 'pieces', 'and', 'orchestrated', 'them', 'and', 'in', 'in', 'the', 'list', 'version', 'which']
Ex Output:
['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF']
Ex Input:
['so', 'in', 'the', 'last', 'video', 'I', 'talked', 'about', 'three-dimensional', 'vector', 'fields', 'and', 'I', 'finish', 'things', 'off', 'with', 'this', 'sort', 'of', 'identity', 'function', 'example', 'where', 'at', 'an', 'input', 'input', 'point', 'XYZ', 'the', 'output', 'vector', 'is', 'also', 'XYZ', 'and', 'here', 'I', 'want', 'to', 'go', 'through', 'a', 'slightly', 'more', 'intricate', 'example', 'so', "I'll", 'go', 'ahead', 'and', 'get', 'rid', 'of', 'this', 'vector', 'field', 'and', 'in', 'this', 'example', 'the', 'X', 'component', 'of', 'the', 'output', 'will', 'be', 'Y', 'times', 'Z', 'the', 'Y', 'component', 'of', 'the', 'output', 'will', 'be', 'x', 'times', 'Z', 'and', 'the', 'Z', 'component', 'of', 'the', 'output', 'will', 'be', 'x', 'times', 'y', 'so', "we'll", 'just']
Ex Output:
['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'STEM_BASED_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF']
Ex Input:
['over', '2,000', 'years', 'ago', 'Euclid', 'showed', 'every', 'number', 'has', 'exactly', 'one', 'prime', 'factorization', 'which', 'we', 'can', 'think', 'of', 'as', 'a', 'secret', 'key', 'it', 'turns', 'out', 'that', 'prime', 'factorization', 'is', 'a', 'fundamentally', 'hard', 'problem', "let's", 'clarify', 'what', 'we', 'mean', 'by', 'easy', 'and', 'hard', 'by', 'introducing', "what's", 'called', 'time', 'complexity', 'we', 'have', 'all', 'multiplied', 'numbers', 'before', 'and', 'each', 'of', 'us', 'has', 'our', 'own', 'rules', 'for', 'doing', 'so', 'in', 'order', 'to', 'speed', 'things', 'up', 'if', 'we', 'program', 'a', 'computer', 'to', 'multiply', 'numbers', 'it', 'can', 'do', 'so', 'much', 'faster', 'than', 'any', 'human', 'can', 'here', 'is', 'a', 'graph', 'that', 'shows', 'the', 'time', 'required', 'for', 'a']
Ex Output:
| ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']
| NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | fs_opt |
You are given a set of queries separated by '
', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.
Input: Consider Input: How does a yam taste like ?
What is the salary for a piano musician ?
How do you verify your account on aqworlds ?
Why is dope called dope ?
Output: How does a yam taste like ?
Input: Consider Input: Who discovered the element Antimony and when ?
How many known elements are there at this time ?
What is the history on plain indians ?
What continent is Curacao located on ?
Output: What is the history on plain indians ?
Input: Consider Input: How do you clean polyester garden furniture ?
Best picture oscar 2001 ?
What is the name of the Russian space probe that visited haley 's comet ?
How can you seperate mixtures ?
| Output: Best picture oscar 2001 ?
| NIv2 | task674_google_wellformed_query_sentence_generation | fs_opt |
Teacher: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.
Teacher: Now, understand the problem? If you are still confused, see the following example:
In one work this author details the life of a tomb-maker who makes extra money by playing the organ at an insane asylum, while another of his novels sees Swartz give a refugee proper documentation only after he tells him his life story in the title Portuguese city. In addition to The Black Obelisk and The Night in Lisbon, he also wrote about Robert and Otto selling their auto workshop and visiting Patrice in a Swiss tuberculosis sanatorium in his novel The Three Comrades, while the turbulent life of the German surgeon Ravic is told in The Arch of Triumph. Another of his novels, The Road Back, is thought to be a sequel to his most famous book, in which the patriotic teacher Kantorek convinces Paul Bumer and his friends to join the Germany Army during World War I. For 10 points, name this German author who wrote All Quiet on the Western Front.
Solution: Literature
Reason: The text is talking about an author and their works, so it belongs to theliterature category.
Now, solve this instance: This man and Blatt name a method for inducing cognitive dissonance by asking questions and then letting the subject spontaneously formulate a response. He used the term "Hierarchic Integration" to describe one of his theories, which relies on a process of conflict resolution called "justice operation." This psychologist proposed a thought experiment in which a man breaks into adrug store to steal for his sick wife. His best-known work was criticized for only examining male subjects in the book In A Different Voice by Carol Gilligan. That work outlines a theory dividing development into three levels: pre-conventional, conventional, and post-conventional. For 10 points, name this psychologist who outlined a six stage theory of moral development.
Student: | Social Science | NIv2 | task521_trivia_question_classification | fs_opt |
You are given a math word problem and you are supposed to apply multiple mathematical operators like addition, subtraction, multiplication or division on the numbers embedded in the text to answer the following question and then only report the final numerical answer.
Example: For the school bake sale Bianca made 14 cupcakes . If she sold 6 of them and then made 17 more , how many cupcakes would she have ?
Example solution: 25
Example explanation: Total cupcakes she would have = baked - sold = 14 -6 + 17 = 25
Problem: There are 43 pencils in the drawer and 19 pencils on the desk . Dan placed 16 pencils on the desk . How many pencils are now there in total ?
| Solution: 78 | NIv2 | task867_mawps_multiop_question_answering | fs_opt |
Evaluate the similarity between them and classify them into classes from 0-5 as follows:
0 : The two sentences are completely dissimilar.
1 : The two sentences are not equivalent, but are on the same topic.
2 : The two sentences are not equivalent, but share some details.
3 : The two sentences are roughly equivalent, but some important information differs/missing.
4 : The two sentences are mostly equivalent, but some unimportant details differ.
5 : The two sentences are completely equivalent, as they mean the same thing.
Example Input: Sentence 1: Operation Chaos is merely people voting. Sentence 2: Chaos is merely people voting.
Example Output: 4
Example Input: Sentence 1: Two people are riding a motorcycle. Sentence 2: Two people are riding a bike.
Example Output: 2
Example Input: Sentence 1: Israel's Peres urges return to peace talks Sentence 2: Israel's Peres calls for return to peace talks
Example Output: | 5
| NIv2 | task1347_glue_sts-b_similarity_classification | fs_opt |
Instructions: In this task, you are given a post in Spanish from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer "hateful" or "Non-hateful". Note that the URLs in the text have been replaced with [Link].
Input: Post: @chochos Pero tú eres puta del PRI
Output: | Hateful | NIv2 | task334_hateeval_classification_hate_es | zs_opt |
You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.
Q: Person1: I have a suggestion . Why don't we go to a ETV and sing ?
Person2:A ETV ? Are you serious ? ETV ?
Person1: Yes , why not ? Don ’ t you like ETV ?
Person2:I don't know . I never went to one .
Person1: Never ? Really ? I'm surprised .
Person2:Many Americans have never gone to a ETV . It ’ s not an American thing to do .
Person1: But there are a lot of Kts in this town . There's one just two blocks from here .
Person2:OK , let's go .
A: | informal | NIv2 | task1533_daily_dialog_formal_classification | zs_opt |
Part 1. Definition
You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with "Description", "Entity", "Abbreviation", "Person", "Quantity", and "Location".
Part 2. Example
What's the most common name in nursery rhymes ?
Answer: Person
Explanation: This question is about people's names. So, the output should be "Person".
Part 3. Exercise
What is the price for tuberculosis drugs ?
Answer: | Quantity | NIv2 | task1289_trec_classification | fs_opt |
In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.
Q: We show that information about whether a neural network's output will be correct or incorrect is present in the outputs of the network's intermediate layers. To demonstrate this effect, we train a new "meta" network to predict from either the final output of the underlying "base" network or the output of one of the base network's intermediate layers whether the base network will be correct or incorrect for a particular input. We find that, over a wide range of tasks and base networks, the meta network can achieve accuracies ranging from 65% - 85% in making this determination.
A: Information about whether a neural network's output will be correct or incorrect is somewhat present in the outputs of the network's intermediate layers.
****
Q: We propose a "plan online and learn offline" framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning. Conversely, we also study how approximate value functions can help reduce the planning horizon and allow for better policies beyond local solutions. Finally, we also demonstrate how trajectory optimization can be used to perform temporally coordinated exploration in conjunction with estimating uncertainty in value function approximation. This exploration is critical for fast and stable learning of the value function. Combining these components enable solutions to complex control tasks, like humanoid locomotion and dexterous in-hand manipulation, in the equivalent of a few minutes of experience in the real world.
A: We propose a framework that incorporates planning for efficient exploration and learning in complex environments.
****
Q: Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.
A: | Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue
****
| NIv2 | task668_extreme_abstract_summarization | fs_opt |
Given the task definition and input, reply with output. In this task, you are given a context paragraph, a question based on that and corresponding answer of a question. Your task is to generate supporting fact/knowledge from context paragraph which helps in answering a given question.
"Can I Be Him" is a song performed by British singer and songwriter James Arthur. The song was released as a digital download on 15 April 2017 in the United Kingdom by Columbia Records as the third single from his second studio album "Back from the Edge" (2016). The song has peaked at number 67 on the Scottish Singles Chart. Question: What season of The X Factor did the singer of Can I Be Him win? Answer: ninth
| Can I Be Him is a song performed by British singer and songwriter James Arthur. | NIv2 | task192_hotpotqa_sentence_generation | zs_opt |
Teacher:In this task, you're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.
Teacher: Now, understand the problem? Solve this instance: Context: For her third movie Link Information: ast.- Shah Rukh Khan as Rahul Khanna, A popular student at St. Xavier's College and Anjali Sharma's best friend. He falls in love with Tina Malhotra and marries her, after which they have a baby girl who is named Anjali. He does not realise his love for Anjali Sharma until he meets her again.
- Kajol as Anjali Sharma, A fun-loving tomboy in college and the best friend of Rahul. Over time, she becomes friends with Tina but also falls in love with Rahul. Once she realises that Rahul and Tina love each other, she is devastated and decides to leave the college.
- Rani Mukerji as Tina Khanna (née Malhotra), The daughter of the principal of St. Xavier's, who is a transfer student from Oxford University. Elegant and sophisticated, she is described as the most beautiful girl in college. She falls in love with Rahul and marries him. The couple has a daughter, but Tina but has always felt guilty about coming between Anjali Sharma and Rahul. She passes away after giving birth, and her last wish is for Rahul to name their child Anjali.
- Salman Khan as Aman Mehra, Anjali Sharma's ex-fiancé.
- Sana Saeed as Anjali Khanna, Named after Anjali Sharma by Tina, she is both Rahul and Tina's daughter. She is independent and fun-loving, and her character mirrors that of Anjali Sharma during the latter's college days. She plays matchmaker between her father and his old college best friend, Anjali Sharma.
- Farida Jalal as Mrs. Savitha Khanna: Rahul's widowed mother. She is very religious and patriotic and supports her granddaughter Anjali in her quest to reunite her father and his best friend. She also constantly irritates Col. Almeida at Camp Sunshine with her patriotism.
- Anupam Kher as Principal Malhotra: Tina's father and the principal of St. Xavier's College. He is slightly infatuated with Ms. Briganza.
- Archana Puran Singh as Ms. Briganza: An English teacher at St. Xavier's. She constantly flirts with Principal Malhotra.
- Reema Lagoo as Mrs. Sharma: She is Anjali Sharma's mother and has doubts about her daughter's desires to marry Aman.
- Himani Shivpuri as Rifat Bi: The St. Xavier's girls' hostel matron. She acts as a motherly figure toward Anjali Sharma.
- Johnny Lever as Col. Almeida: The half-British manager of Camp Sunshine. He is a staunch Anglophile and is thus irritated by the patriotism of Mrs. Khanna.
- Parzan Dastur as Silent Sardarji: A Sikh boy at Camp Sunshine who usually does not speak, but begs Anjali Sharma not to go when she decides to leave the summer camp. He likes Anjali Khanna.
- Neelam Kothari as Neelam (special appearance): She is the host of The Neelam Show, the television programme which Anjali Khanna loves.
- Nikhil Advani in cameo and extra appearance (in Neelam's talk show segment)
- Manish Malhotra in cameo as college student (Sitting on the steps of college when Anjali wears feminine clothing)
- Farah Khan in cameo and extra appearances (in Neelam's talk show and sitting on the steps of college when Anjali wears feminine clothing)
- Geeta Kapoor in the song "Tujhe Yaad Na Meri Aayee"
- Hiroo Johar in cameo as a college professor (walking down the steps of college when Anjali wears feminine clothing)
Answer: Shah Rukh Khan
Student: | Who were Rani's costars in her third movie? | NIv2 | task235_iirc_question_from_subtext_answer_generation | zs_opt |
Detailed Instructions: In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
Q: Not that I'm against plastic surgery but some expectations for people esp women cannot be achieved with a fucking treadmill and squats
A: | No | NIv2 | task609_sbic_potentially_offense_binary_classification | zs_opt |
In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc.
To keep your pens organized on your desktop | you can use a cup to place them in. | NIv2 | task080_piqa_answer_generation | zs_opt |
You will be given a definition of a task first, then some input of the task.
Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.
1 Which cocktail consisting of tequila and triple sac and lemon or lime juice has a name which means daisy in Spanish?
Output: | margarita | NIv2 | task898_freebase_qa_answer_generation | zs_opt |
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Let me give you an example: Head: water<sep>Tail: effect of making things wet
The answer to this example can be: Yes
Here is why: This is a good example. The water can be characterized by making things wet.
OK. solve this:
Head: PersonX answers PersonY's letter<sep>Tail: to invite PersonY
Answer: | No | NIv2 | task1212_atomic_classification_hasproperty | fs_opt |
In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.
One example is below.
Q: Preheat oven to 375 degrees., Boil syrup, sugar and shortening over medium heat, stirring constantly., Remove from heat., Gradually stir in flour and nuts., Drop by teaspoonfuls about 3 inches apart on lightly greased cookie sheet., Bake 5 to 6 min., Remove from oven and let stand 5 min, before removing from sheet., May be rolled into cylindrical shape while still hot., If cooled too much, return to oven for a minute., Yield: 4 dozen cookies.
A: flour, nuts, corn syrup, shortening, brown sugar
Rationale: This is a good example, as we see the NER is generated correctly from the directions.
Q: Simmer cherry juice in a saucepan over medium-high heat, stirring frequently, until the juice is reduced to about 1/2 cup in volume, about 20 to 25 minutes. Remove from heat and pour into a bowl to cool to room temperature., Pour reduced cherry juice, red wine vinegar, and white vinegar together in a blender; add mustard, chile-garlic sauce, salt, and pepper. Blend for 30 seconds. Add a drop of grapeseed oil and blend another 30 seconds. Pour remaining oil into the blender; blend for 2 minutes.
A: | cherry juice, red wine vinegar, white vinegar, mustard, chile-garlic sauce, salt, grapeseed oil | NIv2 | task571_recipe_nlg_ner_generation | fs_opt |
End of preview. Expand
in Dataset Viewer.
README.md exists but content is empty.
- Downloads last month
- 31