Title | COTSAE: CO-Training of Structure and Attribute Embeddings for Entity Alignment |
Authors | Yang, Kai Liu, Shaoqin Zhao, Junfeng Wang, Yasha Xie, Bing |
Affiliation | Minist Educ, Key Lab High Confidence Software Technol, Beijing 100871, Peoples R China Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China Peking Univ, Natl Engn Res Ctr Software Engn, Beijing 100871, Peoples R China Peking Univ, Informat Technol Inst Tianjin Binhai, Tianjin 300450, Peoples R China |
Issue Date | 2020 |
Publisher | THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE |
Abstract | Entity alignment is a fundamental and vital task in Knowl-edge Graph (KG) construction and fusion. Previous works mainly focus on capturing the structural semantics of entities by learning the entity embeddings on the relational triples and pre-aligned "seed entities". Some works also seek to in-corporate the attribute information to assist refining the entity embeddings. However, there are still many problems not considered, which dramatically limits the utilization of attribute information in the entity alignment. Different KGs may have lots of different attribute types, and even the same attribute may have diverse data structures and value granular-ities. Most importantly, attributes may have various "contributions" to the entity alignment. To solve these problems, we propose COTSAE that combines the structure and attribute information of entities by co-training two embedding learning components, respectively. We also propose a joint attention method in our model to learn the attentions of attribute types and values cooperatively. We verified our COTSAE on several datasets from real-world KGs, and the results showed that it is significantly better than the latest entity alignment methods. The structure and attribute information can comple-ment each other and both contribute to performance improvement. |
URI | http://hdl.handle.net/20.500.11897/618423 |
ISBN | 978-1-57735-835-0 |
ISSN | 2159-5399 |
Indexed | CPCI-S(ISTP) |
Appears in Collections: | 信息科学技术学院 软件工程国家工程研究中心 |