Relation Discovery with Out-of-Relation Knowledge Base as Supervision

Yan Liang, Xin Liu, Jianwen Zhang, Yangqiu Song


Abstract
Unsupervised relation discovery aims to discover new relations from a given text corpus without annotated data. However, it does not consider existing human annotated knowledge bases even when they are relevant to the relations to be discovered. In this paper, we study the problem of how to use out-of-relation knowledge bases to supervise the discovery of unseen relations, where out-of-relation means that relations to discover from the text corpus and those in knowledge bases are not overlapped. We construct a set of constraints between entity pairs based on the knowledge base embedding and then incorporate constraints into the relation discovery by a variational auto-encoder based algorithm. Experiments show that our new approach can improve the state-of-the-art relation discovery performance by a large margin.
Anthology ID:
N19-1332
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3280–3290
Language:
URL:
https://aclanthology.org/N19-1332
DOI:
10.18653/v1/N19-1332
Bibkey:
Cite (ACL):
Yan Liang, Xin Liu, Jianwen Zhang, and Yangqiu Song. 2019. Relation Discovery with Out-of-Relation Knowledge Base as Supervision. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3280–3290, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Relation Discovery with Out-of-Relation Knowledge Base as Supervision (Liang et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1332.pdf
Code
 HKUST-KnowComp/RE-RegDVAE
Data
New York Times Annotated Corpus