arXiv:2305.07824
A Simple and Plug-and-play Method for Unsupervised Sentence Representation Enhancement
원문 초록
Generating proper embedding of sentences through an unsupervised way is beneficial to semantic matching and retrieval problems in real-world scenarios. This paper presents Representation ALchemy (RepAL), an extremely simple post-processing method that enhances sentence representations. The basic idea in RepAL is to de-emphasize redundant information of sentence embedding generated by pre-trained models. Through comprehensive experiments, we show that RepAL is free of training and is a plug-and-play method that can be combined with most existing unsupervised sentence learning models. We also conducted in-depth analysis to understand RepAL.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
Mechanistic Decomposition of Sentence Representations
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Multimodal Representation Alignment for Cross-modal Information Retrieval
Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.