Temporal Reasoning on Implicit Events from Distant Supervision

Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth


Abstract
We propose TRACIE, a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events—events that are not mentioned explicitly in natural language text but can be inferred from it. This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events. Human readers can infer implicit events via commonsense reasoning, resulting in a more comprehensive understanding of the situation and, consequently, better reasoning about time. We find, however, that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. To address this, we propose a neuro-symbolic temporal reasoning model, SymTime, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations to infer end times. SymTime outperforms strong baseline systems on TRACIE by 5%, and by 11% in a zero prior knowledge training setting. Our approach also generalizes to other temporal reasoning tasks, as evidenced by a gain of 1%-9% on MATRES, an explicit event benchmark.
Anthology ID:
2021.naacl-main.107
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1361–1371
Language:
URL:
https://aclanthology.org/2021.naacl-main.107
DOI:
10.18653/v1/2021.naacl-main.107
Bibkey:
Cite (ACL):
Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, and Dan Roth. 2021. Temporal Reasoning on Implicit Events from Distant Supervision. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1361–1371, Online. Association for Computational Linguistics.
Cite (Informal):
Temporal Reasoning on Implicit Events from Distant Supervision (Zhou et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.107.pdf
Video:
 https://aclanthology.org/2021.naacl-main.107.mp4