paper-with-me

홈 › Papers

On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning

2022-12-18 · Chenghao Xiao, Yang Long, Noura Al Moubayed

Incorporating contrastive learning objectives in sentence representation learning (SRL) has yielded significant improvements on many sentence-level NLP tasks. However, it is not well understood why contrastive learning works for learning sentence-level semantics. In this paper, we aim to help guide future designs of sentence representation learning methods by taking a closer look at contrastive SRL through the lens of isotropy, contextualization and learning dynamics. We interpret its successes through the geometry of the representation shifts and show that contrastive learning brings isotropy, and drives high intra-sentence similarity: when in the same sentence, tokens converge to similar positions in the semantic space. We also find that what we formalize as "spurious contextualization" is mitigated for semantically meaningful tokens, while augmented for functional ones. We find that the embedding space is directed towards the origin during training, with more areas now better defined. We ablate these findings by observing the learning dynamics with different training temperatures, batch sizes and pooling methods.

📄 PDF Abstract BibTeX arXiv:2212.09170

Code (1)

gowitheflow-1998/on-isotropy-of-contrastive-srl 공식 구현 pytorch

Tasks

Contrastive LearningRepresentation LearningSentenceSentence Similarity

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations

2022-03-14 · ACL 2022 5 · Robert Wolfe, Aylin Caliskan

We examine the effects of contrastive visual semantic pretraining by comparing the geometry and semantic properties of contextualized English language representations formed by GPT-2 and CLIP, a zero-shot multimodal imag…

Image CaptioningSemantic Textual SimilaritySentenceSentence Embeddings+1

Debiased Contrastive Learning of Unsupervised Sentence Representations

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recently, contrastive learning has shown effectiveness in fine-tuning pre-trained language models (PLM) to derive sentence representations, which pulls augmented positive examples together to improve the alignment while …

Contrastive LearningSemantic Textual SimilaritySentence

Whitening Sentence Representations for Better Semantics and Faster Retrieval

2021-03-29 · Jianlin Su, Jiarun Cao, Weijie Liu, Yangyiwen Ou

Pre-training models such as BERT have achieved great success in many natural language processing tasks. However, how to obtain better sentence representation through these pre-training models is still worthy to exploit. …

RetrievalSentence

Debiased Contrastive Learning of Unsupervised Sentence Representations

2022-05-02 · ACL 2022 5 · Kun Zhou, Beichen Zhang, Wayne Xin Zhao, Ji-Rong Wen

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignme…

Contrastive LearningSemantic Textual SimilaritySentence

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

2022-02-27 · Findings (ACL) 2022 5 · Dongyang Li, Taolin Zhang, Nan Hu, Chengyu Wang 외

Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or…

Contrastive LearningData AugmentationRelationRelation Extraction+1