Knowledge Acquisition System Laboratory (Kato Laboratory) aims to develop a system that autonomously acquires knowledge from a large amount of statistical data on the Web, and a search engine that enables users to search for the acquired knowledge. Our laboratory mainly focuses on the following fields in Information Retrieval: retrieval models and ranking, learning to rank, search intent estimation, knowledge base development, knowledge base applications, Web mining, information extraction, search behavior analysis, search user models, recommendation systems, online evaluation.
Our papers “Can a Machine Reading Comprehension Model Improve Ad-hoc Document Retrieval?”, authored by Kota Usuha, Makoto P. Kato, and Sumio Fujita, and “Active Learning for Efficient Partial Improvement of Learning to Rank”, authored by Koki Shibata and Makoto P. Kato, have been accepted at ICADL 2022 as short papers.Read More
Ando-san (M2) and Shinden-san (M1)’s Proposal Got Accepted by 2022 Tsukuba-city’s Project for Supporting Society 5.0 Implementation Trials
A proposal by 合同会社大人検索, which is a company led by Ando-san (M2) and Shinden-san (M1), “Demonstration Experiment of Oudan Sharing ー A System for Enabling Smooth Information Sharing in Organizations by Graph Databases” (グラフデータベースを活用した組織内での情報共有を円滑にするシステム「Oudan Sharing」の実証実験) got accepted by 2022 Tsukuba-city’s project for supporting Society 5.0 implementation trials (令和4年度つくばSociety 5.0社会実装トライアル支援事業). Proposal Overview (in Japanese) (PDF 2.9MB) […]Read More
Usuha-san (M1) received the Poster Presentation Award at the NTCIR-16 Conference! 👏👏👏 Kota Usuha, Kohei Shinden, Makoto P. Kato and Sumio Fujita. KASYS at the NTCIR-16 WWW-4 Task. The 16th NTCIR ConferenceRead More