Back to Search Start Over

Syntax-guided Localized Self-attention by Constituency Syntactic Distance

Authors :
Hou, Shengyuan
Kai, Jushi
Xue, Haotian
Zhu, Bingyu
Yuan, Bo
Huang, Longtao
Wang, Xinbing
Lin, Zhouhan
Publication Year :
2022

Abstract

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information from data is not necessary if we can leverage an external syntactic parser, which provides better parsing quality with well-defined syntactic structures. This could potentially improve Transformer's performance and sample efficiency. In this work, we propose a syntax-guided localized self-attention for Transformer that allows directly incorporating grammar structures from an external constituency parser. It prohibits the attention mechanism to overweight the grammatically distant tokens over close ones. Experimental results show that our model could consistently improve translation performance on a variety of machine translation datasets, ranging from small to large dataset sizes, and with different source languages.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2210.11759
Document Type :
Working Paper