Blindness to Modality Helps Entailment Graph Mining

Liane Guillou, Sander Bijl de Vroe, Mark Johnson, Mark Steedman


Abstract
Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.
Anthology ID:
2021.insights-1.16
Volume:
Proceedings of the Second Workshop on Insights from Negative Results in NLP
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
João Sedoc, Anna Rogers, Anna Rumshisky, Shabnam Tafreshi
Venue:
insights
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
110–116
Language:
URL:
https://aclanthology.org/2021.insights-1.16
DOI:
10.18653/v1/2021.insights-1.16
Bibkey:
Cite (ACL):
Liane Guillou, Sander Bijl de Vroe, Mark Johnson, and Mark Steedman. 2021. Blindness to Modality Helps Entailment Graph Mining. In Proceedings of the Second Workshop on Insights from Negative Results in NLP, pages 110–116, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Blindness to Modality Helps Entailment Graph Mining (Guillou et al., insights 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.insights-1.16.pdf
Video:
 https://aclanthology.org/2021.insights-1.16.mp4
Code
 lianeg/sports-entailment-evaluation