@inproceedings{liu-etal-2020-graph,
    title = "Graph-Based Knowledge Integration for Question Answering over Dialogue",
    author = "Liu, Jian  and
      Sui, Dianbo  and
      Liu, Kang  and
      Zhao, Jun",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2020.coling-main.219/",
    doi = "10.18653/v1/2020.coling-main.219",
    pages = "2425--2435",
    abstract = "Question answering over dialogue, a specialized machine reading comprehension task, aims to comprehend a dialogue and to answer specific questions. Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e.g., relationships between speakers). In this paper, we introduce a new approach for the task, featured by its novelty in structuring dialogue and integrating background knowledge for reasoning. Specifically, different from previous {\textquotedblleft}structure-less{\textquotedblright} approaches, our method organizes a dialogue as a {\textquotedblleft}relational graph{\textquotedblright}, using edges to represent relationships between entities. To encode this relational graph, we devise a relational graph convolutional network (R-GCN), which can traverse the graph`s topological structure and effectively encode multi-relational knowledge for reasoning. The extensive experiments have justified the effectiveness of our approach over competitive baselines. Moreover, a deeper analysis shows that our model is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences."
}