ACL 2021long5 citations

W-RST: Towards a Weighted RST-style Discourse Framework

Patrick Huber, Wen Xiao, Giuseppe Carenini

Abstract

Aiming for a better integration of data-driven and linguistically-inspired approaches, we explore whether RST Nuclearity, assigning a binary assessment of importance between text segments, can be replaced by automatically generated, real-valued scores, in what we call a Weighted-RST framework. In particular, we find that weighted discourse trees from auxiliary tasks can benefit key NLP downstream applications, compared to nuclearity-centered approaches. We further show that real-valued importance distributions partially and interestingly align with the assessment and uncertainty of human annotators.

BibTeX
@inproceedings{huber-etal-2021-w,
    title = "{W}-{RST}: Towards a Weighted {RST}-style Discourse Framework",
    author = "Huber, Patrick  and
      Xiao, Wen  and
      Carenini, Giuseppe",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.302/",
    doi = "10.18653/v1/2021.acl-long.302",
    pages = "3908--3918"
}
W-RST: Towards a Weighted RST-style Discourse Framework · ACL 2021