A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction

Yang Zhou, Tong Zhao, Meng Jiang


Abstract
Textual patterns (e.g., Country’s president Person) are specified and/or generated for extracting factual information from unstructured data. Pattern-based information extraction methods have been recognized for their efficiency and transferability. However, not every pattern is reliable: A major challenge is to derive the most complete and accurate facts from diverse and sometimes conflicting extractions. In this work, we propose a probabilistic graphical model which formulates fact extraction in a generative process. It automatically infers true facts and pattern reliability without any supervision. It has two novel designs specially for temporal facts: (1) it models pattern reliability on two types of time signals, including temporal tag in text and text generation time; (2) it models commonsense constraints as observable variables. Experimental results demonstrate that our model significantly outperforms existing methods on extracting true temporal facts from news data.
Anthology ID:
2020.fever-1.3
Volume:
Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER)
Month:
July
Year:
2020
Address:
Online
Venue:
FEVER
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18–25
Language:
URL:
https://aclanthology.org/2020.fever-1.3
DOI:
10.18653/v1/2020.fever-1.3
Bibkey:
Cite (ACL):
Yang Zhou, Tong Zhao, and Meng Jiang. 2020. A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction. In Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER), pages 18–25, Online. Association for Computational Linguistics.
Cite (Informal):
A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction (Zhou et al., FEVER 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.fever-1.3.pdf
Video:
 http://slideslive.com/38929659