Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Hongyu Lin, Le Sun, Xianpei Han


Abstract
Reasoning with commonsense knowledge is critical for natural language understanding. Traditional methods for commonsense machine comprehension mostly only focus on one specific kind of knowledge, neglecting the fact that commonsense reasoning requires simultaneously considering different kinds of commonsense knowledge. In this paper, we propose a multi-knowledge reasoning method, which can exploit heterogeneous knowledge for commonsense machine comprehension. Specifically, we first mine different kinds of knowledge (including event narrative knowledge, entity semantic knowledge and sentiment coherent knowledge) and encode them as inference rules with costs. Then we propose a multi-knowledge reasoning model, which selects inference rules for a specific reasoning context using attention mechanism, and reasons by summarizing all valid inference rules. Experiments on RocStories show that our method outperforms traditional models significantly.
Anthology ID:
D17-1216
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2032–2043
Language:
URL:
https://www.aclweb.org/anthology/D17-1216
DOI:
10.18653/v1/D17-1216
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1216.pdf
Video:
 https://vimeo.com/238235420