TY - GEN
T1 - Multiple Interaction Attention Model for Open-World Knowledge Graph Completion
AU - Fu, Chenpeng
AU - Li, Zhixu
AU - Yang, Qiang
AU - Chen, Zhigang
AU - Fang, Junhua
AU - Zhao, Pengpeng
AU - Xu, Jiajie
N1 - KAUST Repository Item: Exported on 2020-10-01
PY - 2019/11/14
Y1 - 2019/11/14
N2 - Knowledge Graph Completion (KGC) aims at complementing missing relationships between entities in a Knowledge Graph (KG). While closed-world KGC approaches utilizing the knowledge within KG could only complement very limited number of missing relations, more and more approaches tend to get knowledge from open-world resources such as online encyclopedias and newswire corpus. For instance, a recent proposed open-world KGC model called ConMask learns embeddings of the entity’s name and parts of its text-description to connect unseen entities to the KG. However, this model does not make full use of the rich feature information in the text descriptions, besides, the proposed relationship-dependent content masking method may easily miss to find the target-words. In this paper, we propose to use a Multiple Interaction Attention (MIA) mechanism to model the interactions between the head entity description, head entity name, the relationship name, and the candidate tail entity descriptions, to form the enriched representations. Our empirical study conducted on two real-world data collections shows that our approach achieves significant improvements comparing to state-of-the-art KGC methods.
AB - Knowledge Graph Completion (KGC) aims at complementing missing relationships between entities in a Knowledge Graph (KG). While closed-world KGC approaches utilizing the knowledge within KG could only complement very limited number of missing relations, more and more approaches tend to get knowledge from open-world resources such as online encyclopedias and newswire corpus. For instance, a recent proposed open-world KGC model called ConMask learns embeddings of the entity’s name and parts of its text-description to connect unseen entities to the KG. However, this model does not make full use of the rich feature information in the text descriptions, besides, the proposed relationship-dependent content masking method may easily miss to find the target-words. In this paper, we propose to use a Multiple Interaction Attention (MIA) mechanism to model the interactions between the head entity description, head entity name, the relationship name, and the candidate tail entity descriptions, to form the enriched representations. Our empirical study conducted on two real-world data collections shows that our approach achieves significant improvements comparing to state-of-the-art KGC methods.
UR - http://hdl.handle.net/10754/661852
UR - http://link.springer.com/10.1007/978-3-030-34223-4_40
UR - http://www.scopus.com/inward/record.url?scp=85076998649&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-34223-4_40
DO - 10.1007/978-3-030-34223-4_40
M3 - Conference contribution
SN - 9783030342227
SP - 630
EP - 644
BT - Web Information Systems Engineering – WISE 2019
PB - Springer International Publishing
ER -