Temporal Reasoning in Natural Language Inference

Siddharth Vashishtha, Adam Poliak, Yash Kumar Lal, Benjamin Van Durme, Aaron Steven White


Abstract
We introduce five new natural language inference (NLI) datasets focused on temporal reasoning. We recast four existing datasets annotated for event duration—how long an event lasts—and event ordering—how events are temporally arranged—into more than one million NLI examples. We use these datasets to investigate how well neural models trained on a popular NLI corpus capture these forms of temporal reasoning.
Anthology ID:
2020.findings-emnlp.363
Original:
2020.findings-emnlp.363v1
Version 2:
2020.findings-emnlp.363v2
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4070–4078
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.363
DOI:
10.18653/v1/2020.findings-emnlp.363
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.363.pdf