@inproceedings{hou-etal-2022-syntax,
    title = "Syntax-guided Localized Self-attention by Constituency Syntactic Distance",
    author = "Hou, Shengyuan  and
      Kai, Jushi  and
      Xue, Haotian  and
      Zhu, Bingyu  and
      Yuan, Bo  and
      Huang, Longtao  and
      Wang, Xinbing  and
      Lin, Zhouhan",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.173",
    pages = "2334--2341",
    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.",
}