--- base_model: microsoft/mpnet-base datasets: - SwastikN/sxc_med_llm_chemical_gen language: - en library_name: sentence-transformers license: apache-2.0 metrics: - cosine_accuracy - dot_accuracy - manhattan_accuracy - euclidean_accuracy - max_accuracy pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:117502 - loss:MultipleNegativesRankingLoss widget: - source_sentence: Help me make the molecule CC(=O)OC[C@H](OC(C)=O)C(=O)N1CCCC[C@H]1C1CCN(C(=O)c2cc3ccccc3n2C)CC1 with the same hydrogen bond donors. The output molecule should be similar to the input molecule. Please inform me of the number of hydrogen bond donor(s) of the optimized molecule. sentences: - Your requirements guided the optimization, resulting in the molecule "CC(=O)OC(CCl)C(Cc1cccs1)[C@H](OC(C)=O)C(=O)N1CCCC[C@H]1C1CCN(C(=O)c2cc3ccccc3n2C)CC1" with an approximate hydrogen bond donor(s) of 0. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - source_sentence: How can we modify the molecule CCC(CC)=C(CC)c1ccccc1OC(=O)OC(N=[N+]=[N-])c1ccccc1 to decrease its blood-brain barrier penetration (BBBP) value while keeping it similar to the input molecule? Please inform me of the BBBP value of the optimized molecule. sentences: - Describe a technology used for measuring people's emotional responses. - I've successfully optimized the molecule according to your needs, resulting in "CCOC(=O)c1ccccc1OC(=O)OC(N=[N+]=[N-])c1ccccc1" with an approximate BBBP value of 0.71. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - source_sentence: How can we modify the molecule C/C(=C/C(=O)N1CC[C@H](CC(CCCCCC(CO)C(=O)O)NC(=O)OC(C)(C)C)[C@H]1c1cccnc1)C(=O)O to increase its blood-brain barrier penetration (BBBP) value while keeping it similar to the input molecule? sentences: - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - Aid me in refining a molecular structure written in SMILES notation based on my criteria. - Taking your requirements into account, I've optimized the molecule to "C/C(=C/C(=O)N1CC[C@H](CNC(=O)[C@H](CO)NC(=O)OC(C)(C)C)[C@H]1c1cccnc1)C(=O)O". - source_sentence: Support me in transforming the molecule [SMILES] by incorporating the same hydrogen bond acceptors and maintaining its resemblance to the original molecule. sentences: - Taking your requirements into account, I've optimized the molecule to "CCOc1cccc(C2c3c(oc4ccc(C)cc4c3=O)C(=O)N2CCN(CC)CC)c1". - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - source_sentence: With a molecule represented by the SMILES string CNNNCC(=O)N[C@H](C)C[C@@H](C)NCc1ccc2c(c1)CCC2, propose adjustments that can increase its logP value while keeping the output molecule structurally related to the input molecule. sentences: - Aid me in refining a molecular structure written in SMILES notation based on my criteria. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - In line with your criteria, I've optimized the molecule and present it as "C[C@H](C[C@@H](C)NC(=O)COC(C)(C)C)NCc1ccc2c(c1)CCC2". model-index: - name: MPNet base trained on AllNLI triplets results: - task: type: triplet name: Triplet dataset: name: all nli dev type: all-nli-dev metrics: - type: cosine_accuracy value: 0.6562222222222223 name: Cosine Accuracy - type: dot_accuracy value: 0.5342222222222223 name: Dot Accuracy - type: manhattan_accuracy value: 0.7075555555555556 name: Manhattan Accuracy - type: euclidean_accuracy value: 0.6584444444444445 name: Euclidean Accuracy - type: max_accuracy value: 0.7075555555555556 name: Max Accuracy - type: cosine_accuracy value: 0.9804444444444445 name: Cosine Accuracy - type: dot_accuracy value: 0.01888888888888889 name: Dot Accuracy - type: manhattan_accuracy value: 0.9811111111111112 name: Manhattan Accuracy - type: euclidean_accuracy value: 0.9802222222222222 name: Euclidean Accuracy - type: max_accuracy value: 0.9811111111111112 name: Max Accuracy --- # MPNet base trained on AllNLI triplets This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co./microsoft/mpnet-base) on the [sxc_med_llm_chemical_gen](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [microsoft/mpnet-base](https://huggingface.co./microsoft/mpnet-base) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [sxc_med_llm_chemical_gen](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen) - **Language:** en - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co./models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("Saideepthi55/sentencetransformer-ft") # Run inference sentences = [ 'With a molecule represented by the SMILES string CNNNCC(=O)N[C@H](C)C[C@@H](C)NCc1ccc2c(c1)CCC2, propose adjustments that can increase its logP value while keeping the output molecule structurally related to the input molecule.', 'Given a molecule expressed in SMILES string, help me optimize it according to my requirements.', 'In line with your criteria, I\'ve optimized the molecule and present it as "C[C@H](C[C@@H](C)NC(=O)COC(C)(C)C)NCc1ccc2c(c1)CCC2".', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Triplet * Dataset: `all-nli-dev` * Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) | Metric | Value | |:-------------------|:-----------| | cosine_accuracy | 0.6562 | | dot_accuracy | 0.5342 | | manhattan_accuracy | 0.7076 | | euclidean_accuracy | 0.6584 | | **max_accuracy** | **0.7076** | #### Triplet * Dataset: `all-nli-dev` * Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) | Metric | Value | |:-------------------|:-----------| | cosine_accuracy | 0.9804 | | dot_accuracy | 0.0189 | | manhattan_accuracy | 0.9811 | | euclidean_accuracy | 0.9802 | | **max_accuracy** | **0.9811** | ## Training Details ### Training Dataset #### sxc_med_llm_chemical_gen * Dataset: [sxc_med_llm_chemical_gen](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen) at [ae28874](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen/tree/ae28874de7084969f9aa310b357ac699dbbafa23) * Size: 117,502 training samples * Columns: input, instruction, and output * Approximate statistics based on the first 1000 samples: | | input | instruction | output | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | input | instruction | output | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | | List the countries of the Middle East | Egypt, Israel, Iran, Iraq, Jordan, Kuwait, Lebanon, Qatar, Saudi Arabia, Syria, Turkey, The United Arab Emirates, Oman, and Yemen. | | Support me in refining the molecule CCC(C)=C(CC)c1ccc(Nc2nc3nonc3nc2N2CCC(Oc3ccc(Cl)cc3)CC2)cc1 to have a more drug-like nature, ensuring it remains close to the input molecule. Please inform me of the QED value of the optimized molecule. | Help me adapt a molecular structure denoted in SMILES string based on my preferences. | I've optimized the molecule according to your requirements, yielding the structure "COC(=O)c1ccc(Nc2nc3nonc3nc2N2CCC(Oc3ccc(Cl)cc3)CC2)cc1" and an estimated QED value of 0.4. | | | Create a social media strategy to attract followers on Twitter. | The social media strategy for Twitter should involve Tweeting on a regular basis, with content that is engaging and relevant to the target audience. This can include retweetable quotes, links to videos and articles, sharing photos/images, polls, and so on. It is also beneficial for the information to include hashtags relevant to the content and any relevant topics of the industry.

It is also important to leverage Twitter influencers and accounts, as well as engaging with potential followers regularly and DM them when necessary. Additionally, running campaigns, contests and giveaways to gain more followers should also be part of the strategy. Finally, hashtag research should be conducted to increase the reach of the tweets. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### sxc_med_llm_chemical_gen * Dataset: [sxc_med_llm_chemical_gen](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen) at [ae28874](https://huggingface.co./datasets/SwastikN/sxc_med_llm_chemical_gen/tree/ae28874de7084969f9aa310b357ac699dbbafa23) * Size: 4,500 evaluation samples * Columns: input, instruction, and output * Approximate statistics based on the first 1000 samples: | | input | instruction | output | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | input | instruction | output | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | With a molecule represented by the SMILES string COc1ccc(CN(C(=O)Nc2ccc([C@H](C#N)c3ccccc3)c(Cl)c2)C2CC2)cc1, propose adjustments that can decrease its blood-brain barrier permeability (BBBP) value by at least 0.1 compared to the pre-optimized value while keeping the output molecule structurally related to the input molecule. Please inform me of the BBBP value of the optimized molecule. | Help me adapt a molecular structure denoted in SMILES string based on my preferences. | I've optimized the molecule according to your requirements, yielding the structure "CC(C)c1cccc(Oc2ccc(CN(C(=O)Nc3ccc([C@H](C#N)c4ccccc4)c(Cl)c3)C3CC3)cc2)c1" and an estimated BBBP value of 0.34. | | Which modifications can be applied to the molecule Cc1nn(-c2cc3cc(F)ccc3s2)c2ncc(C(=O)N3CCCC3c3nnc4n3CCCCC4)cc12 to increase its water solubility value while ensuring it remains similar to the original molecule? | Aid me in refining a molecular structure written in SMILES notation based on my criteria. | I've optimized the molecule according to your requirements, resulting in the following structure: "Cc1nn(C)c2ncc(C(=O)N3CCCC3c3nnc4n3CCCCC4)cc12". | | | Describe the benefits of having a mentor. | Having a mentor can provide tremendous benefits, including guidance, advice, support and connection to a network of contacts. Mentors can offer valuable feedback, help to create goals and strategies, and provide the accountability necessary to carry out the desired goals. They can also provide a fresh perspective which can help to create new ideas and solutions. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | loss | all-nli-dev_max_accuracy | |:------:|:----:|:-------------:|:------:|:------------------------:| | 0 | 0 | - | - | 0.7076 | | 0.0174 | 64 | - | - | 0.7156 | | 0.0068 | 100 | 2.7336 | 2.6486 | 0.7524 | | 0.0136 | 200 | 2.4965 | 1.9213 | 0.8162 | | 0.0204 | 300 | 1.9042 | 1.7761 | 0.822 | | 0.0272 | 400 | 1.6856 | 1.7172 | 0.8371 | | 0.0340 | 500 | 1.6117 | 1.6916 | 0.8507 | | 0.0408 | 600 | 1.5673 | 1.6809 | 0.8976 | | 0.0477 | 700 | 1.5984 | 1.7052 | 0.9329 | | 0.0545 | 800 | 1.5828 | 1.6841 | 0.9391 | | 0.0613 | 900 | 1.5375 | 1.6534 | 0.9267 | | 0.0681 | 1000 | 1.5561 | 1.6619 | 0.9509 | | 0.0749 | 1100 | 1.4911 | 1.6538 | 0.9556 | | 0.0817 | 1200 | 1.5075 | 1.6498 | 0.966 | | 0.0885 | 1300 | 1.4722 | 1.6468 | 0.946 | | 0.0953 | 1400 | 1.4806 | 1.6981 | 0.9631 | | 0.1021 | 1500 | 1.4788 | 1.6335 | 0.9662 | | 0.1089 | 1600 | 1.4668 | 1.6668 | 0.9731 | | 0.1157 | 1700 | 1.4383 | 1.6473 | 0.9711 | | 0.1225 | 1800 | 1.4549 | 1.6462 | 0.9713 | | 0.1294 | 1900 | 1.4394 | 1.6184 | 0.9718 | | 0.1362 | 2000 | 1.3861 | 1.6156 | 0.9676 | | 0.1430 | 2100 | 1.4111 | 1.6045 | 0.9711 | | 0.1498 | 2200 | 1.4286 | 1.6056 | 0.9782 | | 0.1566 | 2300 | 1.4669 | 1.6174 | 0.9764 | | 0.1634 | 2400 | 1.3761 | 1.6182 | 0.9776 | | 0.1702 | 2500 | 1.4119 | 1.6150 | 0.9738 | | 0.1770 | 2600 | 1.3625 | 1.5984 | 0.9776 | | 0.1838 | 2700 | 1.3726 | 1.6092 | 0.9807 | | 0.1906 | 2800 | 1.3265 | 1.6059 | 0.9789 | | 0.1974 | 2900 | 1.3925 | 1.6004 | 0.978 | | 0.2042 | 3000 | 1.3524 | 1.5964 | 0.9773 | | 0.2111 | 3100 | 1.342 | 1.6213 | 0.9787 | | 0.2179 | 3200 | 1.3478 | 1.6016 | 0.9822 | | 0.2247 | 3300 | 1.3888 | 1.6038 | 0.9793 | | 0.2315 | 3400 | 1.3328 | 1.5977 | 0.9813 | | 0.2383 | 3500 | 1.372 | 1.6114 | 0.9824 | | 0.2451 | 3600 | 1.3046 | 1.6082 | 0.9824 | | 0.2519 | 3700 | 1.3857 | 1.5922 | 0.9824 | | 0.2587 | 3800 | 1.3236 | 1.6127 | 0.9809 | | 0.2655 | 3900 | 1.2929 | 1.5935 | 0.9824 | | 0.2723 | 4000 | 1.3889 | 1.6047 | 0.9831 | | 0.2791 | 4100 | 1.3509 | 1.6030 | 0.9844 | | 0.2859 | 4200 | 1.3455 | 1.6099 | 0.9824 | | 0.2928 | 4300 | 1.337 | 1.5939 | 0.984 | | 0.2996 | 4400 | 1.3302 | 1.6057 | 0.9827 | | 0.3064 | 4500 | 1.3377 | 1.6254 | 0.9833 | | 0.3132 | 4600 | 1.3221 | 1.6020 | 0.9849 | | 0.3200 | 4700 | 1.3209 | 1.6146 | 0.9824 | | 0.3268 | 4800 | 1.354 | 1.6022 | 0.9824 | | 0.3336 | 4900 | 1.3213 | 1.6136 | 0.9822 | | 0.3404 | 5000 | 1.3484 | 1.5920 | 0.9807 | | 0.3472 | 5100 | 1.3412 | 1.6106 | 0.978 | | 0.3540 | 5200 | 1.3532 | 1.6001 | 0.9784 | | 0.3608 | 5300 | 1.2984 | 1.6192 | 0.9762 | | 0.3676 | 5400 | 1.3621 | 1.5850 | 0.98 | | 0.3745 | 5500 | 1.2839 | 1.6158 | 0.9807 | | 0.3813 | 5600 | 1.3664 | 1.6030 | 0.9831 | | 0.3881 | 5700 | 1.327 | 1.6168 | 0.9822 | | 0.3949 | 5800 | 1.3123 | 1.6040 | 0.982 | | 0.4017 | 5900 | 1.3019 | 1.6092 | 0.9824 | | 0.4085 | 6000 | 1.3908 | 1.5935 | 0.9829 | | 0.4153 | 6100 | 1.3136 | 1.5916 | 0.9791 | | 0.4221 | 6200 | 1.32 | 1.6091 | 0.9807 | | 0.4289 | 6300 | 1.3018 | 1.6052 | 0.9827 | | 0.4357 | 6400 | 1.3144 | 1.6083 | 0.9816 | | 0.4425 | 6500 | 1.2865 | 1.6015 | 0.9829 | | 0.4493 | 6600 | 1.2946 | 1.5882 | 0.9818 | | 0.4562 | 6700 | 1.3245 | 1.5949 | 0.9824 | | 0.4630 | 6800 | 1.3278 | 1.6081 | 0.9831 | | 0.4698 | 6900 | 1.2842 | 1.6086 | 0.9836 | | 0.4766 | 7000 | 1.3231 | 1.6170 | 0.9811 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.1.0 - Transformers: 4.44.2 - PyTorch: 2.4.0+cu121 - Accelerate: 0.34.2 - Datasets: 3.0.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```