paper-with-me

Papers

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

2022-04-21 · NAACL 2022 7 · Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljačić, Shang-Wen Li, Wen-tau Yih, Yoon Kim, James Glass

We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the edited sentence is obtained by stochastically masking out the original sentence and then sampling from a masked language model. We show that DiffSCE is an instance of equivariant contrastive learning (Dangovski et al., 2021), which generalizes contrastive learning and learns representations that are insensitive to certain types of augmentations and sensitive to other "harmful" types of augmentations. Our experiments show that DiffCSE achieves state-of-the-art results among unsupervised sentence representation learning methods, outperforming unsupervised SimCSE by 2.3 absolute points on semantic textual similarity tasks.

📄 PDF Abstract BibTeX arXiv:2204.10298

Code (1)

voidism/diffcse 공식 구현 jax

Tasks

Contrastive LearningLanguage ModelingLanguage ModellingRepresentation LearningSemantic Textual SimilaritySentenceSentence Embeddings

Methods 이 논문이 사용한 방법론

SimCSE SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in…
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives

2023-05-22 · Jiahao Xu, Wei Shao, Lihui Chen, Lemao Liu

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout nois…

Contrastive LearningSentenceSentence Embeddings

D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings

2023-04-18 · Hyunjae Lee

This paper describes Difference-aware Deep continuous prompt for Contrastive Sentence Embeddings (D2CSE) that learns sentence embeddings. Compared to state-of-the-art approaches, D2CSE computes sentence vectors that are …

Contrastive LearningRetrievalSemantic Textual SimilaritySentence+2

KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning

2024-03-26 · Cong-Duy Nguyen, Thong Nguyen, Xiaobao Wu, Anh Tuan Luu

Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results. However, by taking the rest of the batch as negative samples without reviewing when forming cont…

Contrastive LearningKnowledge DistillationSemantic Textual SimilaritySentence+4

SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings

2024-04-25 · Kang Liu

Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured informati…

Contrastive LearningInformation RetrievalRetrievalSentence+4

Sentence Embeddings using Supervised Contrastive Learning

2021-06-09 · Danqi Liao

Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thought…

Contrastive LearningSemantic Textual SimilaritySentenceSentence Embeddings+1