Papers › An Unsupervised Sentence Embedding Method by Mutual Information Maximization

An Unsupervised Sentence Embedding Method by Mutual Information Maximization

25 Sep 2020EMNLP 2020 11arXiv:2009.12061archive 2025-07-28

Yan Zhang, Ruidan He, Zuozhu Liu, Kwan Hui Lim, Lidong Bing

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.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yanzhangnlp/IS-BERT officialpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Clustering STS Self-Supervised Learning Semantic Textual Similarity Sentence Sentence Embedding Sentence Embeddings Sentence-Embedding

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Textual Similarity	SICK	IS-BERT-NLI	Spearman Correlation	0.6425	#22 of 22	Archive leaderboard	report
Semantic Textual Similarity	STS Benchmark	IS-BERT-NLI	Spearman Correlation	0.6921	#61 of 66	Archive leaderboard	report
Semantic Textual Similarity	STS12	IS-BERT-NLI	Spearman Correlation	0.5677	#20 of 20	Archive leaderboard	report
Semantic Textual Similarity	STS13	IS-BERT-NLI	Spearman Correlation	0.6924	#22 of 22	Archive leaderboard	report
Semantic Textual Similarity	STS14	IS-BERT-NLI	Spearman Correlation	0.6121	#21 of 21	Archive leaderboard	report
Semantic Textual Similarity	STS15	IS-BERT-NLI	Spearman Correlation	0.7523	#19 of 20	Archive leaderboard	report
Semantic Textual Similarity	STS16	IS-BERT-NLI	Spearman Correlation	0.7016	#20 of 20	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection SBERT Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections