Multi-Relational Script Learning for Discourse Relations

I-Ta Lee, Dan Goldwasser


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 model 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.
Anthology ID:
P19-1413
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4214–4226
Language:
URL:
https://aclanthology.org/P19-1413
DOI:
10.18653/v1/P19-1413
Bibkey:
Cite (ACL):
I-Ta Lee and Dan Goldwasser. 2019. Multi-Relational Script Learning for Discourse Relations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4214–4226, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Multi-Relational Script Learning for Discourse Relations (Lee & Goldwasser, ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/P19-1413.pdf
Video:
 https://preview.aclanthology.org/ingest-bitext-workshop/P19-1413.mp4
Code
 doug919/multi_relational_script_learning