Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition

Huibin Ruan; Yu Hong; Yang Xu; Zhen Huang; Guodong Zhou; Min Zhang

COLING 2020main28 citations

Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition

Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, Min Zhang

Abstract

We tackle implicit discourse relation recognition. Both self-attention and interactive-attention mechanisms have been applied for attention-aware representation learning, which improves the current discourse analysis models. To take advantages of the two attention mechanisms simultaneously, we develop a propagative attention learning model using a cross-coupled two-channel network. We experiment on Penn Discourse Treebank. The test results demonstrate that our model yields substantial improvements over the baselines (BiLSTM and BERT).

BibTeX

@inproceedings{ruan-etal-2020-interactively,
    title = "Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition",
    author = "Ruan, Huibin  and
      Hong, Yu  and
      Xu, Yang  and
      Huang, Zhen  and
      Zhou, Guodong  and
      Zhang, Min",
    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://aclanthology.org/2020.coling-main.282/",
    doi = "10.18653/v1/2020.coling-main.282",
    pages = "3168--3178"
}