arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01767cs.CL
收藏

WhiteningBERT:一种简单的无监督句子嵌入方法

WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach

Beihang University(北京航空航天大学);Microsoft Research Asia(微软亚洲研究院);Sun Yat-sen University(中山大学);Peking University(北京大学);Microsoft STC Asia(微软亚太研发集团)

Junjie Huang, Duyu Tang, Wanjun Zhong, Shuai Lu, Linjun Shou, Ming Gong, Daxin Jiang, Nan Duan

摘要:

以无监督的方式产生句子的嵌入对于自然语言匹配和检索问题在实践中是有价值的。在这项工作中,我们对基于预训练模型的无监督句子嵌入进行了彻底的检查。我们研究了四个预训练模型,并在七个关于句子语义的数据集上进行了大量实验。我们有主要的发现。首先,平均所有令牌比只使用[CLS]向量更好。第二,将顶层和底层结合起来比只使用顶层要好。最后,一个简单的基于白化的向量归一化策略,不到10行代码,始终提高了性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑