Multi-Relational Script Learning for Discourse Relations

I-Ta Lee     Dan Goldwasser    
Association for Computational Linguistics (ACL), 2019
[pdf]

Abstract

Modeling script knowledge can be useful for a wide range of NLP tasks. Current statistical script learning approaches embed the events, such that their relationships are indicated by their similarity in the embedding. While intuitive, these approaches fall short of representing nuanced relations, needed for downstream tasks. In this paper, we suggest to view learning event embedding as a multi-relational problem, which allows us to capture different aspects of event pairs. We model a rich set of event relations, such as Cause and Contrast, derived from the Penn Discourse Tree Bank. We evaluate our models on three types of tasks, the popular Mutli-Choice Narrative Cloze and its variants, several multi-relational prediction tasks, and a related downstream task---implicit discourse sense classification.


Bib Entry

  @InProceedings{LG_acl_2019,
    author = "I-Ta Lee and Dan Goldwasser",
    title = "Multi-Relational Script Learning for Discourse Relations",
    booktitle = "Association for Computational Linguistics (ACL)",
    year = "2019"
  }