@inproceedings{chen-etal-2022-modeling-compositionality,
    title = "Modeling Compositionality with Dependency Graph for Dialogue Generation",
    author = "Chen, Xiaofeng  and
      Chen, Yirong  and
      Xing, Xiaofen  and
      Xu, Xiangmin  and
      Han, Wenjing  and
      Tie, Qianfeng",
    editor = "Chen, Wenhu  and
      Chen, Xinyun  and
      Chen, Zhiyu  and
      Yao, Ziyu  and
      Yasunaga, Michihiro  and
      Yu, Tao  and
      Zhang, Rui",
    booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)",
    month = jul,
    year = "2022",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.suki-1.2",
    doi = "10.18653/v1/2022.suki-1.2",
    pages = "9--16",
    abstract = "Because of the compositionality of natural language, syntactic structure which contains the information about the relationship between words is a key factor for semantic understanding. However, the widely adopted Transformer is hard to learn the syntactic structure effectively in dialogue generation tasks. To explicitly model the compositionaity of language in Transformer Block, we restrict the information flow between words by constructing directed dependency graph and propose Dependency Relation Attention (DRA). Experimental results demonstrate that DRA can further improve the performance of state-of-the-art models for dialogue generation.",
}