WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach
Junjie Huang, Duyu Tang, Wanjun Zhong, Shuai Lu, Linjun Shou, Ming Gong, Daxin Jiang, Nan Duan
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 three main findings. First, averaging all tokens is better than only using [CLS] vector. Second, combining both top and bottom 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.