TIMEDIAL: Temporal Commonsense Reasoning in Dialog

Lianhui Qin, Aditya Gupta, Shyam Upadhyay, Luheng He, Yejin Choi, Manaal Faruqui


Abstract
Everyday conversations require understanding everyday events, which in turn, requires understanding temporal commonsense concepts interwoven with those events. Despite recent progress with massive pre-trained language models (LMs) such as T5 and GPT-3, their capability of temporal reasoning in dialogs remains largely under-explored. In this paper, we present the first study to investigate pre-trained LMs for their temporal reasoning capabilities in dialogs by introducing a new task and a crowd-sourced English challenge set, TimeDial. We formulate TimeDial as a multiple choice cloze task with over 1.1K carefully curated dialogs. Empirical results demonstrate that even the best performing models struggle on this task compared to humans, with 23 absolute points of gap in accuracy. Furthermore, our analysis reveals that the models fail to reason about dialog context correctly; instead, they rely on shallow cues based on existing temporal patterns in context, motivating future research for modeling temporal concepts in text and robust contextual reasoning about them. The dataset is publicly available at https://github.com/google-research-datasets/timedial.
Anthology ID:
2021.acl-long.549
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7066–7076
Language:
URL:
https://aclanthology.org/2021.acl-long.549
DOI:
10.18653/v1/2021.acl-long.549
Bibkey:
Cite (ACL):
Lianhui Qin, Aditya Gupta, Shyam Upadhyay, Luheng He, Yejin Choi, and Manaal Faruqui. 2021. TIMEDIAL: Temporal Commonsense Reasoning in Dialog. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7066–7076, Online. Association for Computational Linguistics.
Cite (Informal):
TIMEDIAL: Temporal Commonsense Reasoning in Dialog (Qin et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.549.pdf
Optional supplementary material:
 2021.acl-long.549.OptionalSupplementaryMaterial.zip
Video:
 https://aclanthology.org/2021.acl-long.549.mp4
Code
 google-research-datasets/timedial
Data
TimeDialDailyDialog