Year: 2023
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institution: Tencent (China)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4376653016