Relation Prediction for Unseen-Entities Using Entity-Word Graphs

Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, Keiichi Nemoto


Abstract
Knowledge graphs (KGs) are generally used for various NLP tasks. However, as KGs still miss some information, it is necessary to develop Knowledge Graph Completion (KGC) methods. Most KGC researches do not focus on the Out-of-KGs entities (Unseen-entities), we need a method that can predict the relation for the entity pairs containing Unseen-entities to automatically add new entities to the KGs. In this study, we focus on relation prediction and propose a method to learn entity representations via a graph structure that uses Seen-entities, Unseen-entities and words as nodes created from the descriptions of all entities. In the experiments, our method shows a significant improvement in the relation prediction for the entity pairs containing Unseen-entities.
Anthology ID:
D19-5302
Volume:
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
Month:
November
Year:
2019
Address:
Hong Kong
Venues:
EMNLP | TextGraphs | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11–16
Language:
URL:
https://aclanthology.org/D19-5302
DOI:
10.18653/v1/D19-5302
Bibkey:
Cite (ACL):
Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, and Keiichi Nemoto. 2019. Relation Prediction for Unseen-Entities Using Entity-Word Graphs. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 11–16, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Relation Prediction for Unseen-Entities Using Entity-Word Graphs (Tagawa et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5302.pdf