An Unsupervised Sentence Embedding Method by Mutual Information Maximization

By Yan Zhang, Ruidan He, Zuozhu Liu, Kwan Hui Lim, Lidong Bing. 2020

197 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Parameter-Efficient Transfer Learning with Diff Pruning (2020, background): “…that can be used without finetuning for downstream tasks (Le & Mikolov, 2014; Kiros et al., 2015; Wieting et al., 2016; Hill et al., 2016; Arora et al., 2017; Conneau et al., 2017; Cer et al., 2018; Zhang et al., 2018; Subramanian et al., 2018; Reimers & Gurevych, 2019; Zhang et al., 2020b).”
SimCSE: Simple Contrastive Learning of Sentence Embeddings (2021, methodology): “Several recent (and concurrent) approaches adopt contrastive objectives (Zhang et al., 2020; Giorgi et al., 2021; Wu et al., 2020; Meng et al., 2021; Carlsson et al., 2021; Kim et al., 2021; Yan et al., 2021) by taking different views—from data augmentation or different copies of models—of the same ”
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021, methodology): “, 2020) (trained on BookCorpus and English Wikipedia corpus), ISBERT (Zhang et al., 2020) (trained on unlabeled texts from NLI datasets), BERT-CT (Carlsson et al.”
Intent Contrastive Learning for Sequential Recommendation (2022, background): “Contrastive Self-Supervised Learning (SSL) has brought much attentions by different research communities including CV [2, 4, 9, 14, 20] and NLP [7, 8, 29, 50], as well as recommendation [44, 45, 47, 51].”
AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing (2021, methodology): “Recently many approaches based on supervised learning [190], [191] or self-supervised learning [158], [159], [192]–[194], [194], [195] are proposed.”
Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity (2024, background): “Given that this is merely a simple linear mapping, it is likely that some vital manually annotated information is lost, potentially hindering Pcc-tuning from reaching its optimal performance on the evaluation benchmarks.”