--- base_model: BAAI/bge-base-en-v1.5 datasets: [] language: - en library_name: sentence-transformers license: apache-2.0 metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:196 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: The text refers to the preparation of a pre-trained model for data set usage, which is a crucial step in machine learning projects. This suggests that the project involves using a model that has already been trained on a dataset, which can then be fine-tuned or used directly for specific tasks, potentially saving time and computational resources. sentences: - What is the significance of preparing a pre-trained model in the data set for the process described in the text? - What is the purpose of the document? - What are the developer AI developer's experiences in AI development and research? - source_sentence: The project manager has a degree from Vietnam National University and has completed a Google TensorFlow certification. sentences: - How often are the training, evaluation, and re-training steps repeated in the text? - What is the project manager's educational background? - What information should be shared via email when final product delivery is completed? - source_sentence: The text mentions that Docker for the deployment of a high NT Q trained model was built between July 18 and July 19, 2024. sentences: - What is the role of "データベースベクトルとセマンティクス検索モジュール"? - When was the Docker for the deployment of a high NT Q trained model built? - What is the significance of Level 3 in the escalation process described in the text? - source_sentence: The text spans from September 4th to October 16th, covering a total of 33 days. sentences: - How many days are listed in the given text? - How does the system support the current system and plan for future feature development? - What are the two distinct products offered by NT Q? - source_sentence: After text generation, the process involves providing test data to NT Q, which then undergoes article correction, including dealing with fragmented articles and errors. sentences: - What is the process for providing test data to NT Q after text generation? - When is the deadline for combining the API for the setting function? - What is the significance of the dates in the text? model-index: - name: BGE base Financial Matryoshka results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.7755102040816326 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8775510204081632 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9591836734693877 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9795918367346939 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.7755102040816326 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2925170068027211 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19183673469387752 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09795918367346937 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.7755102040816326 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8775510204081632 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9591836734693877 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9795918367346939 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8776251324776435 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.8447845804988664 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.846354439211582 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.7959183673469388 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8979591836734694 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9591836734693877 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9795918367346939 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.7959183673469388 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.29931972789115646 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19183673469387752 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09795918367346937 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.7959183673469388 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8979591836734694 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9591836734693877 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9795918367346939 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.884559158446073 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.8539358600583091 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.8551363402503859 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.6938775510204082 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9183673469387755 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9591836734693877 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9591836734693877 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.6938775510204082 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.3061224489795918 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19183673469387752 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09591836734693876 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.6938775510204082 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.9183673469387755 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9591836734693877 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9591836734693877 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8397332987260313 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7993197278911565 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.8016520894071916 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.6938775510204082 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9183673469387755 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9183673469387755 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9183673469387755 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.6938775510204082 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.3061224489795918 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1836734693877551 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09183673469387756 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.6938775510204082 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.9183673469387755 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9183673469387755 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9183673469387755 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8168105921282822 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7823129251700681 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.7865583396195641 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.5918367346938775 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.7959183673469388 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8163265306122449 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9183673469387755 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.5918367346938775 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.26530612244897955 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.16326530612244897 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09183673469387756 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.5918367346938775 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.7959183673469388 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8163265306122449 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9183673469387755 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7471061057082727 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6929057337220603 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6978234213668709 name: Cosine Map@100 --- # BGE base Financial Matryoshka This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co./BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co./BAAI/bge-base-en-v1.5) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **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': True}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## 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("cngcv/bge-base-financial-matryoshka") # Run inference sentences = [ 'After text generation, the process involves providing test data to NT Q, which then undergoes article correction, including dealing with fragmented articles and errors.', 'What is the process for providing test data to NT Q after text generation?', 'What is the significance of the dates in the text?', ] 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 #### Information Retrieval * Dataset: `dim_768` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.7755 | | cosine_accuracy@3 | 0.8776 | | cosine_accuracy@5 | 0.9592 | | cosine_accuracy@10 | 0.9796 | | cosine_precision@1 | 0.7755 | | cosine_precision@3 | 0.2925 | | cosine_precision@5 | 0.1918 | | cosine_precision@10 | 0.098 | | cosine_recall@1 | 0.7755 | | cosine_recall@3 | 0.8776 | | cosine_recall@5 | 0.9592 | | cosine_recall@10 | 0.9796 | | cosine_ndcg@10 | 0.8776 | | cosine_mrr@10 | 0.8448 | | **cosine_map@100** | **0.8464** | #### Information Retrieval * Dataset: `dim_512` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.7959 | | cosine_accuracy@3 | 0.898 | | cosine_accuracy@5 | 0.9592 | | cosine_accuracy@10 | 0.9796 | | cosine_precision@1 | 0.7959 | | cosine_precision@3 | 0.2993 | | cosine_precision@5 | 0.1918 | | cosine_precision@10 | 0.098 | | cosine_recall@1 | 0.7959 | | cosine_recall@3 | 0.898 | | cosine_recall@5 | 0.9592 | | cosine_recall@10 | 0.9796 | | cosine_ndcg@10 | 0.8846 | | cosine_mrr@10 | 0.8539 | | **cosine_map@100** | **0.8551** | #### Information Retrieval * Dataset: `dim_256` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.6939 | | cosine_accuracy@3 | 0.9184 | | cosine_accuracy@5 | 0.9592 | | cosine_accuracy@10 | 0.9592 | | cosine_precision@1 | 0.6939 | | cosine_precision@3 | 0.3061 | | cosine_precision@5 | 0.1918 | | cosine_precision@10 | 0.0959 | | cosine_recall@1 | 0.6939 | | cosine_recall@3 | 0.9184 | | cosine_recall@5 | 0.9592 | | cosine_recall@10 | 0.9592 | | cosine_ndcg@10 | 0.8397 | | cosine_mrr@10 | 0.7993 | | **cosine_map@100** | **0.8017** | #### Information Retrieval * Dataset: `dim_128` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.6939 | | cosine_accuracy@3 | 0.9184 | | cosine_accuracy@5 | 0.9184 | | cosine_accuracy@10 | 0.9184 | | cosine_precision@1 | 0.6939 | | cosine_precision@3 | 0.3061 | | cosine_precision@5 | 0.1837 | | cosine_precision@10 | 0.0918 | | cosine_recall@1 | 0.6939 | | cosine_recall@3 | 0.9184 | | cosine_recall@5 | 0.9184 | | cosine_recall@10 | 0.9184 | | cosine_ndcg@10 | 0.8168 | | cosine_mrr@10 | 0.7823 | | **cosine_map@100** | **0.7866** | #### Information Retrieval * Dataset: `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.5918 | | cosine_accuracy@3 | 0.7959 | | cosine_accuracy@5 | 0.8163 | | cosine_accuracy@10 | 0.9184 | | cosine_precision@1 | 0.5918 | | cosine_precision@3 | 0.2653 | | cosine_precision@5 | 0.1633 | | cosine_precision@10 | 0.0918 | | cosine_recall@1 | 0.5918 | | cosine_recall@3 | 0.7959 | | cosine_recall@5 | 0.8163 | | cosine_recall@10 | 0.9184 | | cosine_ndcg@10 | 0.7471 | | cosine_mrr@10 | 0.6929 | | **cosine_map@100** | **0.6978** | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 196 training samples * Columns: positive and anchor * Approximate statistics based on the first 1000 samples: | | positive | anchor | |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | positive | anchor | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | The document lists several tasks with their statuses, such as "Done", "In progress", and "To be done". These statuses indicate the current progress of each task within the project. For example, "Set up environment" and "Set up development environment" are marked as "Done", suggesting these tasks have been completed, while "Build translation data set" is marked as "In progress", indicating it is currently being worked on. | What is the status of the project tasks mentioned in the document? | | The 'Web Application Construction' task is mentioned to be completed by NT Q, with a duration from July 17, 2023, to July 28, 2023, and is marked as 'Done' with a completion of 10 tasks. | What is the scope of the 'Web Application Construction' task? | | "RE F" could potentially stand for "Reference File" or "Record File," indicating that this text might be part of a larger dataset or document used for reference or record-keeping purposes. | What is the significance of the "RE F" at the beginning of the text? | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 16 - `gradient_accumulation_steps`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `tf32`: False - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 16 - `eval_accumulation_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`: 4 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `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`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: False - `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`: True - `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_fused - `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 - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| | 1.0 | 1 | 0.6908 | 0.7097 | 0.8111 | 0.6240 | 0.8011 | | 2.0 | 2 | 0.7292 | 0.7692 | 0.8177 | 0.6634 | 0.8162 | | 3.0 | 3 | 0.7555 | 0.8014 | 0.8541 | 0.6992 | 0.8451 | | **4.0** | **4** | **0.7866** | **0.8017** | **0.8551** | **0.6978** | **0.8464** | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.13 - Sentence Transformers: 3.0.1 - Transformers: 4.42.3 - PyTorch: 2.1.2 - Accelerate: 0.32.1 - Datasets: 2.20.0 - 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", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### 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} } ```