NAACL 2021long15 citations

Predicting Discourse Trees from Transformer-based Neural Summarizers

Wen Xiao, Patrick Huber, Giuseppe Carenini

Abstract

Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summarizers. In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model. Experiments across models and datasets reveal that the summarizer learns both, dependency- and constituency-style discourse information, which is typically encoded in a single head, covering long- and short-distance discourse dependencies. Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain.

BibTeX
@inproceedings{xiao-etal-2021-predicting,
    title = "Predicting Discourse Trees from Transformer-based Neural Summarizers",
    author = "Xiao, Wen  and
      Huber, Patrick  and
      Carenini, Giuseppe",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.326/",
    doi = "10.18653/v1/2021.naacl-main.326",
    pages = "4139--4152"
}
Predicting Discourse Trees from Transformer-based Neural Summarizers · NAACL 2021