A Simple And Plug-and-play Method For Unsupervised Sentence Representation Enhancement
Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi . Arxiv 2023 – 1 citation
[Paper]
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.