Presentation information

General Session

General Session » [GS] J-4 Knowledge utilization and sharing

[1K2-J-4] Knowledge utilization and sharing 1

Tue. Jun 4, 2019 1:20 PM - 3:00 PM Room K (201A Medium meeting room)

Chair:Naoki Fukuda Reviewer:Jun Sugiura

1:40 PM - 2:00 PM

[1K2-J-4-02] Multi-Domain Knowledge Base Construction System Based on Various Data Integration

〇Tomoya Yamazaki1, Takuya Makabe1, Kentaro Nishi1, Chihiro Nishimoto1, Hiroki Iwasawa1 (1. Yahoo Japan Corporation)

Keywords:Knowledge Base, Entity Matching, Ontology

Knowledge bases play crucial roles in a wide variety of information systems, such as search engines and intelligent personal assistants. For responding constantly fluctuating user information demands, we aim to construct a large-scale and well-structured multi-domain knowledge base from the world’s evolving data. In this paper, we discuss enterprise-specific issues with knowledge base construction and present how to deal with these issues in our construction system. To maintain the quality of our knowledge base at the production-level, our construction system is carefully designed to incorporate various automatic and manual validation methods. We partly leverage manual validation methods to deal with business requirements and user feedback quickly since it is difficult to filter out all incorrect facts automatically in practice. Our constructed knowledge base is already utilized in real-world Japanese Web services, and the number of entities in it keeps growing steadily.