arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15316cs.CLcs.AIcs.LG
收藏

白化句子表示以获得更好的语义和更快的检索

Whitening Sentence Representations for Better Semantics and Faster Retrieval

Shenzhen Zhuiyi Technology Co., Ltd.(深圳市追一科技有限公司);Tencent Research(腾讯研究院)

Jianlin Su, Jiarun Cao, Weijie Liu, Yangyiwen Ou

摘要:

预训练模型如BERT在许多自然语言处理任务中取得了巨大的成功。然而,如何通过这些预训练模型获得更好的句子表示仍然值得探索。以往的研究表明,各向异性问题是基于BERT的句子表示的一个关键瓶颈,它阻碍了模型充分利用底层语义特征。因此,一些增强句子分布均匀性的尝试,如基于流的模型,被应用到句子表示中,并取得了一定的改进。在本文中,我们发现传统机器学习中的白化操作可以类似地增强句子表示的各向同性,并获得有竞争力的结果。此外,白化技术还能够降低句子表示的维数。实验结果表明,该方法不仅能获得良好的性能,而且能显著降低存储开销,加快模型检索速度。

英文摘要:

Pre-training models such as BERT have achieved great success in many natural language processing tasks. However, how to obtain better sentence representation through these pre-training models is still worthy to exploit. Previous work has shown that the anisotropy problem is an critical bottleneck for BERT-based sentence representation which hinders the model to fully utilize the underlying semantic features. Therefore, some attempts of boosting the isotropy of sentence distribution, such as flow-based model, have been applied to sentence representations and achieved some improvement. In this paper, we find that the whitening operation in traditional machine learning can similarly enhance the isotropy of sentence representations and achieve competitive results. Furthermore, the whitening technique is also capable of reducing the dimensionality of the sentence representation. Our experimental results show that it can not only achieve promising performance but also significantly reduce the storage cost and accelerate the model retrieval speed.

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。

↑