{"url":"/task/sentence-embeddings","name":"Sentence Embeddings","slug":"sentence-embeddings","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":615,"papers_with_code":255,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":4,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/wikimatrix","name":"WikiMatrix","full_name":"","num_papers_in_archive":91},{"url":"/dataset/scanrefer-dataset","name":"ScanRefer Dataset","full_name":"","num_papers_in_archive":63},{"url":"/dataset/pit","name":"PIT","full_name":"Paraphrase and Semantic Similarity in Twitter","num_papers_in_archive":22},{"url":"/dataset/discovery","name":"Discovery","full_name":"","num_papers_in_archive":10},{"url":"/dataset/sts-2014","name":"SemEval-2014 Task-10","full_name":"","num_papers_in_archive":6},{"url":"/dataset/geocov19","name":"GeoCoV19","full_name":"","num_papers_in_archive":4},{"url":"/dataset/auxad","name":"AuxAD","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/auxai","name":"AuxAI","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/costra-1-0","name":"COSTRA 1.0","full_name":"","num_papers_in_archive":1},{"url":"/dataset/french-cass-dataset","name":"French CASS dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gloreplus","name":"GloREPlus","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/joint-multilingual-sentence-representations","name":"Joint Multilingual Sentence Representations"},{"url":"/task/sentence-compression","name":"Sentence Compression"},{"url":"/task/sentence-embedding","name":"Sentence Embedding"},{"url":"/task/sentence-embeddings-for-biomedical-texts","name":"Sentence Embeddings For Biomedical Texts"}],"parent_tasks":[{"url":"/task/representation-learning","name":"Representation Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":255,"tagged_in_all":615,"items":[{"url":"/paper/sentence-bert-sentence-embeddings-using","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","date":"2019-08-27","arxiv_id":"1908.10084","repositories_listed":64,"syntology":{"n":58,"n_ran":20,"n_unverified":38,"n_pointer_only":11}},{"url":"/paper/universal-sentence-encoder","title":"Universal Sentence Encoder","date":"2018-03-29","arxiv_id":"1803.11175","repositories_listed":24,"syntology":{"n":22,"n_ran":1,"n_unverified":21,"n_pointer_only":1}},{"url":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","arxiv_id":"2104.08821","repositories_listed":23,"syntology":{"n":30,"n_ran":17,"n_unverified":13,"n_pointer_only":19}},{"url":"/paper/evaluation-of-sentence-embeddings-in","title":"Evaluation of sentence embeddings in downstream and linguistic probing tasks","date":"2018-06-16","arxiv_id":"1806.06259","repositories_listed":14,"syntology":null},{"url":"/paper/massively-multilingual-sentence-embeddings","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","date":"2018-12-26","arxiv_id":"1812.10464","repositories_listed":13,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/making-monolingual-sentence-embeddings","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","date":"2020-04-21","arxiv_id":"2004.09813","repositories_listed":12,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/margin-based-parallel-corpus-mining-with","title":"Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings","date":"2018-11-03","arxiv_id":"1811.01136","repositories_listed":9,"syntology":null},{"url":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","arxiv_id":"2104.06979","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","date":"2020-07-03","arxiv_id":"2007.01852","repositories_listed":6,"syntology":null},{"url":"/paper/wikimatrix-mining-135m-parallel-sentences-in","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","date":"2019-07-10","arxiv_id":"1907.05791","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/what-you-can-cram-into-a-single-vector","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","date":"2018-05-03","arxiv_id":"1805.01070","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/unsupervised-learning-of-sentence-embeddings","title":"Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features","date":"2017-03-07","arxiv_id":"1703.02507","repositories_listed":5,"syntology":null},{"url":"/paper/colbert-using-bert-sentence-embedding-for","title":"ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor","date":"2020-04-27","arxiv_id":"2004.12765","repositories_listed":4,"syntology":null},{"url":"/paper/simple-and-effective-paraphrastic-similarity-1","title":"Simple and Effective Paraphrastic Similarity from Parallel Translations","date":"2019-09-30","arxiv_id":"1909.13872","repositories_listed":4,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","arxiv_id":"1810.09302","repositories_listed":4,"syntology":null},{"url":"/paper/learning-natural-language-inference-with-lstm","title":"Learning Natural Language Inference with LSTM","date":"2015-12-30","arxiv_id":"1512.08849","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/rediscovering-hashed-random-projections-for","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","date":"2023-03-13","arxiv_id":"2304.02481","repositories_listed":3,"syntology":null},{"url":"/paper/on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","arxiv_id":"2011.05864","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pre-training-is-a-hot-topic-contextualized","title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence","date":"2020-04-08","arxiv_id":"2004.03974","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/scanrefer-3d-object-localization-in-rgb-d","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","date":"2019-12-18","arxiv_id":"1912.08830","repositories_listed":3,"syntology":null},{"url":"/paper/augmenting-data-with-mixup-for-sentence","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","date":"2019-05-22","arxiv_id":"1905.08941","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/categorization-of-comparative-sentences-for","title":"Categorizing Comparative Sentences","date":"2018-09-17","arxiv_id":"1809.06152","repositories_listed":3,"syntology":null},{"url":"/paper/hyperbolic-neural-networks","title":"Hyperbolic Neural Networks","date":"2018-05-23","arxiv_id":"1805.09112","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/simple-unsupervised-keyphrase-extraction","title":"Simple Unsupervised Keyphrase Extraction using Sentence Embeddings","date":"2018-01-13","arxiv_id":"1801.04470","repositories_listed":3,"syntology":null},{"url":"/paper/dissent-sentence-representation-learning-from","title":"DisSent: Sentence Representation Learning from Explicit Discourse Relations","date":"2017-10-12","arxiv_id":"1710.04334","repositories_listed":3,"syntology":null},{"url":"/paper/dependency-sensitive-convolutional-neural","title":"Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents","date":"2016-11-08","arxiv_id":"1611.02361","repositories_listed":3,"syntology":null},{"url":"/paper/fine-grained-analysis-of-sentence-embeddings","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","date":"2016-08-15","arxiv_id":"1608.04207","repositories_listed":3,"syntology":null},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-extractive-dialogue","title":"Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space","date":"2024-05-16","arxiv_id":"2405.09765","repositories_listed":2,"syntology":null},{"url":"/paper/simple-techniques-for-enhancing-sentence","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","date":"2024-04-05","arxiv_id":"2404.03921","repositories_listed":2,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}