WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach
Computation and Language
2021-04-12 v3
Abstract
Producing the embedding of a sentence in an unsupervised way is valuable to natural language matching and retrieval problems in practice. In this work, we conduct a thorough examination of pretrained model based unsupervised sentence embeddings. We study on four pretrained models and conduct massive experiments on seven datasets regarding sentence semantics. We have there main findings. First, averaging all tokens is better than only using [CLS] vector. Second, combining both top andbottom layers is better than only using top layers. Lastly, an easy whitening-based vector normalization strategy with less than 10 lines of code consistently boosts the performance.
Keywords
Cite
@article{arxiv.2104.01767,
title = {WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach},
author = {Junjie Huang and Duyu Tang and Wanjun Zhong and Shuai Lu and Linjun Shou and Ming Gong and Daxin Jiang and Nan Duan},
journal= {arXiv preprint arXiv:2104.01767},
year = {2021}
}