@inproceedings{chen-etal-2017-improved,
    title = "Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder",
    author = "Chen, Huadong  and
      Huang, Shujian  and
      Chiang, David  and
      Chen, Jiajun",
    editor = "Barzilay, Regina  and
      Kan, Min-Yen",
    booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P17-1177/",
    doi = "10.18653/v1/P17-1177",
    pages = "1936--1945",
    abstract = "Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. More specifically, we propose (1) a bidirectional tree encoder which learns both sequential and tree structured representations; (2) a tree-coverage model that lets the attention depend on the source-side syntax. Experiments on Chinese-English translation demonstrate that our proposed models outperform the sequential attentional model as well as a stronger baseline with a bottom-up tree encoder and word coverage."
}