An Unsupervised Sentence Embedding Method by Mutual Information Maximization
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.
Code (1)
Tasks
ClusteringSelf-Supervised LearningSemantic Textual SimilaritySentenceSentence EmbeddingSentence-EmbeddingSentence EmbeddingsSTSMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Mutual Information Maximization Perspective of Language Representation Learning
We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation …
Representation LearningSentenceAn Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning
Unsupervised sentence embeddings learning has been recently dominated by contrastive learning methods (e.g., SimCSE), which keep positive pairs similar and push negative pairs apart. The contrast operation aims to keep a…
Contrastive LearningRepresentation LearningSemantic Textual SimilaritySentence+3Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long dependency structures, these methods rarely model the raw documents directly, but inst…
AttributeSemi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization
Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supe…
Formality Style TransferLanguage ModelingLanguage ModellingSemi-Supervised Formality Style Transfer+4APS: Active Pretraining with Successor Features
We introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information between tasks and states induced by the poli…
Unsupervised Reinforcement Learning