{"url":"/task/sentence-embedding-1","name":"Sentence-Embedding","slug":"sentence-embedding-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":381,"papers_with_code":155,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/glue","name":"GLUE","full_name":"General Language Understanding Evaluation benchmark","num_papers_in_archive":3197},{"url":"/dataset/cards-against-humanity","name":"Cards Against Humanity","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mcqueen","name":"McQueen","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":155,"tagged_in_all":381,"items":[{"url":"/paper/a-structured-self-attentive-sentence","title":"A Structured Self-attentive Sentence Embedding","date":"2017-03-09","arxiv_id":"1703.03130","repositories_listed":52,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":2}},{"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/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/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/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/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/sbert-wk-a-sentence-embedding-method-by","title":"SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models","date":"2020-02-16","arxiv_id":"2002.06652","repositories_listed":3,"syntology":null},{"url":"/paper/disan-directional-self-attention-network-for","title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","date":"2017-09-14","arxiv_id":"1709.04696","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/aligning-books-and-movies-towards-story-like","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","date":"2015-06-22","arxiv_id":"1506.06724","repositories_listed":3,"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},{"url":"/paper/sentence-embedding-models-for-ancient-greek","title":"Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation","date":"2023-08-24","arxiv_id":"2308.13116","repositories_listed":2,"syntology":null},{"url":"/paper/micse-mutual-information-contrastive-learning","title":"miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings","date":"2022-11-09","arxiv_id":"2211.04928","repositories_listed":2,"syntology":null},{"url":"/paper/kernel-whitening-overcome-dataset-bias-with","title":"Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding","date":"2022-10-14","arxiv_id":"2210.07547","repositories_listed":2,"syntology":null},{"url":"/paper/infocse-information-aggregated-contrastive","title":"InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings","date":"2022-10-08","arxiv_id":"2210.06432","repositories_listed":2,"syntology":null},{"url":"/paper/esimcse-enhanced-sample-building-method-for","title":"ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding","date":"2021-09-09","arxiv_id":"2109.04380","repositories_listed":2,"syntology":null},{"url":"/paper/smoothed-contrastive-learning-for","title":"Smoothed Contrastive Learning for Unsupervised Sentence Embedding","date":"2021-09-09","arxiv_id":"2109.04321","repositories_listed":2,"syntology":null},{"url":"/paper/a-bilingual-generative-transformer-for-1","title":"A Bilingual Generative Transformer for Semantic Sentence Embedding","date":"2019-11-10","arxiv_id":"1911.03895","repositories_listed":2,"syntology":null},{"url":"/paper/sentence-embedding-alignment-for-lifelong","title":"Sentence Embedding Alignment for Lifelong Relation Extraction","date":"2019-03-06","arxiv_id":"1903.02588","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-embed-sentences-using-attentive","title":"Learning to Embed Sentences Using Attentive Recursive Trees","date":"2018-11-06","arxiv_id":"1811.02338","repositories_listed":2,"syntology":null},{"url":"/paper/neural-sentence-embedding-using-only-in","title":"Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems","date":"2018-07-27","arxiv_id":"1807.11567","repositories_listed":2,"syntology":null},{"url":"/paper/learning-semantic-sentence-embeddings-using-1","title":"Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator","date":"2018-06-03","arxiv_id":"1806.00807","repositories_listed":2,"syntology":{"n":17,"n_ran":4,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/contrastive-prompting-enhances-sentence","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","date":"2025-05-19","arxiv_id":"2505.12831","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transformer-embeddings","title":"Parameter-Efficient Transformer Embeddings","date":"2025-05-04","arxiv_id":"2505.02266","repositories_listed":1,"syntology":null},{"url":"/paper/information-leakage-of-sentence-embeddings","title":"Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks","date":"2025-04-23","arxiv_id":"2504.16609","repositories_listed":1,"syntology":null},{"url":"/paper/ipcgrl-language-instructed-reinforcement","title":"IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation","date":"2025-03-16","arxiv_id":"2503.12358","repositories_listed":1,"syntology":null},{"url":"/paper/fanchuan-a-multilingual-and-graph-structured","title":"FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis","date":"2025-02-23","arxiv_id":"2502.16503","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-rwkv-for-sentence-embeddings-layer","title":"Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity","date":"2025-02-20","arxiv_id":"2502.14620","repositories_listed":1,"syntology":null},{"url":"/paper/refining-sentence-embedding-model-through","title":"Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models","date":"2025-02-19","arxiv_id":"2502.13656","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}