{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-unsupervised-sentence-embedding-method","title":"An Unsupervised Sentence Embedding Method by Mutual Information Maximization","arxiv_id":"2009.12061","date":"2020-09-25","proceeding":"EMNLP 2020 11","authors":["Yan Zhang","Ruidan He","Zuozhu Liu","Kwan Hui Lim","Lidong Bing"],"abstract":"BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning semantically meaningful representations of single sentences, such that similarity comparison can be easily accessed. However, SBERT is trained on corpus with high-quality labeled sentence pairs, which limits its application to tasks where labeled data is extremely scarce. In this paper, we propose a lightweight extension on top of BERT and a novel self-supervised learning objective based on mutual information maximization strategies to derive meaningful sentence embeddings in an unsupervised manner. Unlike SBERT, our method is not restricted by the availability of labeled data, such that it can be applied on different domain-specific corpus. Experimental results show that the proposed method significantly outperforms other unsupervised sentence embedding baselines on common semantic textual similarity (STS) tasks and downstream supervised tasks. It also outperforms SBERT in a setting where in-domain labeled data is not available, and achieves performance competitive with supervised methods on various tasks.","url_abs":"https://arxiv.org/abs/2009.12061v2","url_pdf":"https://arxiv.org/pdf/2009.12061v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-unsupervised-sentence-embedding-method","repo_url":"https://github.com/yanzhangnlp/IS-BERT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sbert","method_name":"SBERT"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-textual-similarity-on-sick","task":"Semantic Textual Similarity","dataset":"SICK","model":"IS-BERT-NLI","rank_in_archive_order":22,"of":22,"metrics":{"Spearman Correlation":"0.6425"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"IS-BERT-NLI","rank_in_archive_order":61,"of":66,"metrics":{"Spearman Correlation":"0.6921"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts12","task":"Semantic Textual Similarity","dataset":"STS12","model":"IS-BERT-NLI","rank_in_archive_order":20,"of":20,"metrics":{"Spearman Correlation":"0.5677"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts13","task":"Semantic Textual Similarity","dataset":"STS13","model":"IS-BERT-NLI","rank_in_archive_order":22,"of":22,"metrics":{"Spearman Correlation":"0.6924"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"IS-BERT-NLI","rank_in_archive_order":21,"of":21,"metrics":{"Spearman Correlation":"0.6121"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts15","task":"Semantic Textual Similarity","dataset":"STS15","model":"IS-BERT-NLI","rank_in_archive_order":19,"of":20,"metrics":{"Spearman Correlation":"0.7523"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"IS-BERT-NLI","rank_in_archive_order":20,"of":20,"metrics":{"Spearman Correlation":"0.7016"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.12061","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}