Spaces:
Running
Running
File size: 3,369 Bytes
6e8d046 3dc1d5a 6e8d046 3dc1d5a 6e8d046 3dc1d5a 6e8d046 3dc1d5a 6e8d046 3dc1d5a 6e8d046 3dc1d5a 6e8d046 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
import torch
import streamlit as st
from transformers import RobertaTokenizer, RobertaForSequenceClassification
import re
import string
def tokenize_sentences(sentence):
encoded_dict = tokenizer.encode_plus(
sentence,
add_special_tokens=True,
max_length=128,
padding='max_length',
truncation=True,
return_attention_mask=True,
return_tensors='pt'
)
return torch.cat([encoded_dict['input_ids']], dim=0), torch.cat([encoded_dict['attention_mask']], dim=0)
def preprocess_query(query):
query = str(query).lower()
query = query.strip()
query=query.translate(str.maketrans("", "", string.punctuation))
return query
def predict_aspects(sentence, threshold):
input_ids, attention_mask = tokenize_sentences(sentence)
with torch.no_grad():
outputs = aspects_model(input_ids, attention_mask=attention_mask)
logits = outputs.logits
predicted_aspects = torch.sigmoid(logits).squeeze().tolist()
results = dict()
for label, prediction in zip(LABEL_COLUMNS_ASPECTS, predicted_aspects):
if prediction < threshold:
continue
precentage = round(float(prediction) * 100, 2)
results[label] = precentage
return results
# Load tokenizer and model
BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION = 'roberta-base'
tokenizer = RobertaTokenizer.from_pretrained(BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION, do_lower_case=True)
# Define the aspect labels
LABEL_COLUMNS_ASPECTS = [
'FOOD-CUISINE', 'FOOD-DEALS', 'FOOD-DIET_OPTION', 'FOOD-EXPERIENCE', 'FOOD-FLAVOR',
'FOOD-GENERAL', 'FOOD-INGREDIENT', 'FOOD-KITCHEN', 'FOOD-MEAL', 'FOOD-MENU',
'FOOD-PORTION', 'FOOD-PRESENTATION', 'FOOD-PRICE', 'FOOD-QUALITY', 'FOOD-RECOMMENDATION',
'FOOD-TASTE', 'GENERAL-GENERAL', 'RESTAURANT-ATMOSPHERE', 'RESTAURANT-BUILDING',
'RESTAURANT-DECORATION', 'RESTAURANT-EXPERIENCE', 'RESTAURANT-FEATURES',
'RESTAURANT-GENERAL', 'RESTAURANT-HYGIENE', 'RESTAURANT-KITCHEN', 'RESTAURANT-LOCATION',
'RESTAURANT-OPTIONS', 'RESTAURANT-RECOMMENDATION', 'RESTAURANT-SEATING_PLAN',
'RESTAURANT-VIEW', 'SERVICE-BEHAVIOUR', 'SERVICE-EXPERIENCE', 'SERVICE-GENERAL',
'SERVICE-WAIT_TIME'
]
# Load the model with the specified number of labels
aspects_model = RobertaForSequenceClassification.from_pretrained(
BERT_MODEL_NAME_FOR_ASPECTS_CLASSIFICATION,
num_labels=len(LABEL_COLUMNS_ASPECTS)
)
# Load the state dictionary
aspects_model.load_state_dict(torch.load('./Aspects_Extraction_Model_updated.pth', map_location=torch.device('cpu')), strict=False)
# Set the model to evaluation mode
aspects_model.eval()
# Streamlit App
st.title("Implicit and Explicit Aspect Extraction")
sentence = st.text_input("Enter a sentence:")
threshold = st.slider("Threshold", min_value=0.0, max_value=1.0, step=0.01, value=0.5)
if sentence:
processed_sentence = preprocess_query(sentence)
results = predict_aspects(processed_sentence, threshold)
if len(results) > 0:
st.write("Predicted Aspects:")
table_data = [["Category","Aspect", "Probability"]]
for aspect, percentage in results.items():
aspect_parts = aspect.split("-")
table_data.append(aspect_parts + [f"{percentage}%"])
st.table(table_data)
else:
st.write("No aspects above the threshold.")
|