WIQA: A dataset for “What if...” reasoning over procedural text

Niket Tandon, Bhavana Dalvi, Keisuke Sakaguchi, Peter Clark, Antoine Bosselut


Abstract
We introduce WIQA, the first large-scale dataset of “What if...” questions over procedural text. WIQA contains a collection of paragraphs, each annotated with multiple influence graphs describing how one change affects another, and a large (40k) collection of “What if...?” multiple-choice questions derived from these. For example, given a paragraph about beach erosion, would stormy weather hasten or decelerate erosion? WIQA contains three kinds of questions: perturbations to steps mentioned in the paragraph; external (out-of-paragraph) perturbations requiring commonsense knowledge; and irrelevant (no effect) perturbations. We find that state-of-the-art models achieve 73.8% accuracy, well below the human performance of 96.3%. We analyze the challenges, in particular tracking chains of influences, and present the dataset as an open challenge to the community.
Anthology ID:
D19-1629
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6076–6085
Language:
URL:
https://www.aclweb.org/anthology/D19-1629
DOI:
10.18653/v1/D19-1629
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1629.pdf
Attachment:
 D19-1629.Attachment.zip