COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi


Abstract
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.
Anthology ID:
P19-1470
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4762–4779
Language:
URL:
https://aclanthology.org/P19-1470
DOI:
10.18653/v1/P19-1470
Bibkey:
Cite (ACL):
Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019. COMET: Commonsense Transformers for Automatic Knowledge Graph Construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4762–4779, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (Bosselut et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1470.pdf
Data
ConceptNet