paper-with-me

Papers

A Simple and Plug-and-play Method for Unsupervised Sentence Representation Enhancement

2023-05-13 · Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi

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.

📄 PDF Abstract BibTeX arXiv:2305.07824

Code (0)

등록된 구현이 없습니다.

Tasks

RetrievalSentenceSentence EmbeddingSentence-Embedding

Similar Papers 제목 키워드 기반

RepAL: A Simple and Plug-and-play Method for Improving Unsupervised Sentence Representations

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

Unsupervised sentence representation learning is a fundamental problem in natural language processing and has been studied extensively in recent years. This paper presents Representation ALchemy (RepAL), an extremely sim…

Representation LearningSentenceSentence EmbeddingSentence-Embedding

Alleviating Over-smoothing for Unsupervised Sentence Representation

2023-05-09 · Nuo Chen, Linjun Shou, Ming Gong, Jian Pei 외

Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language models (PLMs) and contrastive learning hav…

Contrastive LearningSemantic Textual SimilaritySentence

Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering

2023-05-15 · Bing Wang, Ximing Li, Zhiyao Yang, Yuanyuan Guan 외

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, result…

Language ModellingRepresentation LearningSentenceSentence Embeddings

Unsupervised Document Embedding via Contrastive Augmentation

2021-03-26 · Dongsheng Luo, Wei Cheng, Jingchao Ni, Wenchao Yu 외

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image …

Contrastive LearningData AugmentationDocument ClassificationDocument Embedding+3

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

2017-03-07 · NAACL 2018 6 · Matteo Pagliardini, Prakhar Gupta, Martin Jaggi

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word s…

SentenceSentence EmbeddingsWord Embeddings