paper-with-me

홈 › Papers

HiCL: Hierarchical Contrastive Learning of Unsupervised Sentence Embeddings

2023-10-15 · Zhuofeng Wu, Chaowei Xiao, VG Vinod Vydiswaran

In this paper, we propose a hierarchical contrastive learning framework, HiCL, which considers local segment-level and global sequence-level relationships to improve training efficiency and effectiveness. Traditional methods typically encode a sequence in its entirety for contrast with others, often neglecting local representation learning, leading to challenges in generalizing to shorter texts. Conversely, HiCL improves its effectiveness by dividing the sequence into several segments and employing both local and global contrastive learning to model segment-level and sequence-level relationships. Further, considering the quadratic time complexity of transformers over input tokens, HiCL boosts training efficiency by first encoding short segments and then aggregating them to obtain the sequence representation. Extensive experiments show that HiCL enhances the prior top-performing SNCSE model across seven extensively evaluated STS tasks, with an average increase of +0.2% observed on BERT-large and +0.44% on RoBERTa-large.

📄 PDF Abstract BibTeX arXiv:2310.09720

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation LearningSentenceSentence EmbeddingsSTS

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings

2022-01-28 · Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu 외

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success …

Contrastive LearningOpen-Ended Question AnsweringSentenceSentence Embeddings+1

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

2022-04-21 · NAACL 2022 7 · Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang 외

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 sen…

Contrastive LearningLanguage ModelingLanguage ModellingRepresentation Learning+3

UNSEE: Unsupervised Non-contrastive Sentence Embeddings

2024-01-27 · Ömer Veysel Çağatan

We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation c…

SentenceSentence Embeddings

Contrastive Learning of Sentence Embeddings from Scratch

2023-05-24 · Junlei Zhang, Zhenzhong Lan, Junxian He

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language in…

Contrastive LearningNatural Language InferenceRerankingSentence+2

BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels

2026-04-17 · Mengfei Lan, Lecheng Zheng, Halil Kilicoglu arxiv

Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build on coarse binary relevance signals, lim…

Biomedical Information RetrievalContrastive LearningQuestion Answering