# An Unsupervised Sentence Embedding Method by Mutual Information Maximization

arXiv: https://arxiv.org/abs/2009.12061 · HTML: https://mlsanity.com/paper/2009.12061/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 30 of 91)

- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings](https://mlsanity.com/paper/2204.10298/) (2022)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [Intent Contrastive Learning for Sequential Recommendation](https://mlsanity.com/paper/2202.02519/) (2022)
- [Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders](https://mlsanity.com/paper/2104.08027/) (2021)
- [PromptBERT: Improving BERT Sentence Embeddings with Prompts](https://mlsanity.com/paper/2201.04337/) (2022)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach](https://mlsanity.com/paper/2104.01767/) (2021)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning](https://mlsanity.com/paper/2410.20964/) (2024)
- [BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings](https://mlsanity.com/paper/2311.05296/) (2023)
- [Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning](https://mlsanity.com/paper/2203.06875/) (2022)
- [PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings](https://mlsanity.com/paper/2201.12093/) (2022)
- [InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2210.06432/) (2022)
- [Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding](https://mlsanity.com/paper/2202.13093/) (2022)
- [RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank](https://mlsanity.com/paper/2305.16726/) (2023)
- [MCSE: Multimodal Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2204.10931/) (2022)
- [Virtual Augmentation Supported Contrastive Learning of Sentence Representations](https://mlsanity.com/paper/2110.08552/) (2021)
- [Whitening-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2305.17746/) (2023)
- [Just Rank: Rethinking Evaluation with Word and Sentence Similarities](https://mlsanity.com/paper/2203.02679/) (2022)
- [SCD: Self-Contrastive Decorrelation for Sentence Embeddings](https://mlsanity.com/paper/2203.07847/) (2022)
- [DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2109.12599/) (2021)
- [Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework](https://mlsanity.com/paper/2210.16798/) (2022)
- [Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision](https://mlsanity.com/paper/2206.14719/) (2022)
- [Meaning Representations from Trajectories in Autoregressive Models](https://mlsanity.com/paper/2310.18348/) (2023)
- [Alleviating Over-smoothing for Unsupervised Sentence Representation](https://mlsanity.com/paper/2305.06154/) (2023)

## Abstract (arXiv)

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.