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

[1K2-J-4-04] Report on the First Knowledge Graph Reasoning Challenge 2018

- Toward the eXplainable AI System -

○Takahiro Kawamura^1,2, Shusaku Egami², Koutarou Tamura^3,4, Yasunori Hokazono⁴, Takanori Ugai⁵, Yusuke Koyanagi⁵, Fumihito Nishino⁵, Seiji Okajima⁵, Katsuhiko Murakami⁵, Kunihiko Takamatsu⁶, Aoi Sugiura⁷, Shun Shiramatsu⁸, Xiangyu Zhang⁸, Kouji Kozaki⁹ (1. Japan Science and Technology Agency, 2. University of Electro-Communications, 3. NRI digital, Ltd., 4. Nomura Research Institute, Ltd., 5. Fujitsu Laboratories Ltd., 6. Kobe Tokiwa University, 7. Kobe City Nishi-Kobe Medical Center, 8. Nagoya Institute of Technology, 9. Osaka University)

Keywords:Knowledge Graph, Explainablity, Reasoning, Machine Learning

New challenges for knowledge graph reasoning started in Japan in 2018. Machine learning techniques have promoted applying systems containing AI to a wide variety of social systems. The explanation for the AI decision is becoming important to guarantee the security and safety of such AI systems to a certain extent. Therefore, the Special Interest Group on Semantic Web and Ontology of JSAI organized this challenge, which calls for techniques for reasoning and/or estimating criminals with a reasonable explanation based on an open knowledge graph representing a well-known novel of Sherlock Holmes. This paper describes a summary report of the first challenge, including the knowledge graph constructed for this task, approaches proposed for reasoning and/or estimating, and the evaluation metrics. Finally, we conclude this paper with the plans and issues for the next challenge in 2019.