Exploratory Neural Relation Classification for Domain Knowledge Acquisition

Yan Fan, Chengyu Wang, Xiaofeng He


Abstract
The state-of-the-art methods for relation classification are primarily based on deep neural net- works. This kind of supervised learning method suffers from not only limited training data, but also the large number of low-frequency relations in specific domains. In this paper, we propose the task of exploratory relation classification for domain knowledge harvesting. The goal is to learn a classifier on pre-defined relations and discover new relations expressed in texts. A dynamically structured neural network is introduced to classify entity pairs to a continuously expanded relation set. We further propose the similarity sensitive Chinese restaurant process to discover new relations. Experiments conducted on a large corpus show the effectiveness of our neural network, while new relations are discovered with high precision and recall.
Anthology ID:
C18-1192
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2265–2276
Language:
URL:
https://aclanthology.org/C18-1192
DOI:
Bibkey:
Cite (ACL):
Yan Fan, Chengyu Wang, and Xiaofeng He. 2018. Exploratory Neural Relation Classification for Domain Knowledge Acquisition. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2265–2276, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Exploratory Neural Relation Classification for Domain Knowledge Acquisition (Fan et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1192.pdf