INFOTABS: Inference on Tables as Semi-structured Data

Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, Vivek Srikumar


Abstract
In this paper, we observe that semi-structured tabulated text is ubiquitous; understanding them requires not only comprehending the meaning of text fragments, but also implicit relationships between them. We argue that such data can prove as a testing ground for understanding how we reason about information. To study this, we introduce a new dataset called INFOTABS, comprising of human-written textual hypotheses based on premises that are tables extracted from Wikipedia info-boxes. Our analysis shows that the semi-structured, multi-domain and heterogeneous nature of the premises admits complex, multi-faceted reasoning. Experiments reveal that, while human annotators agree on the relationships between a table-hypothesis pair, several standard modeling strategies are unsuccessful at the task, suggesting that reasoning about tables can pose a difficult modeling challenge.
Anthology ID:
2020.acl-main.210
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2309–2324
Language:
URL:
https://aclanthology.org/2020.acl-main.210
DOI:
10.18653/v1/2020.acl-main.210
Bibkey:
Cite (ACL):
Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, and Vivek Srikumar. 2020. INFOTABS: Inference on Tables as Semi-structured Data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2309–2324, Online. Association for Computational Linguistics.
Cite (Informal):
INFOTABS: Inference on Tables as Semi-structured Data (Gupta et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.210.pdf
Software:
 2020.acl-main.210.Software.zip
Dataset:
 2020.acl-main.210.Dataset.zip
Video:
 http://slideslive.com/38929232
Data
InfoTabSGLUEMultiNLISNLISQuADTabFact