• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2022 Fiscal Year Final Research Report

Conversationalisation of Search Interaction Based on Verbalisation of Search Intents

Research Project

  • PDF
Project/Area Number 19H04418
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 90020:Library and information science, humanistic and social informatics-related
Research InstitutionUniversity of Tsukuba

Principal Investigator

Joho Hideo  筑波大学, 図書館情報メディア系, 教授 (00571184)

Co-Investigator(Kenkyū-buntansha) 松林 麻実子  筑波大学, 図書館情報メディア系, 講師 (10359581)
于 海涛  筑波大学, 図書館情報メディア系, 准教授 (30751052)
Project Period (FY) 2019-04-01 – 2023-03-31
Keywords情報検索 / 会話検索
Outline of Final Research Achievements

This research "Conversationalisation of Search Interaction Based on Verbalisation of Search Intents" considers technical issues of conversational search systems from the viewpoint of enhancing conversationalization of search interaction, by (1) collecting search intents/tactics, (2) constructing a database of linguistic expressions of search intents/tactics, (3) analyzing estimation of linguistic expressions of search intents/tactics, and (4) developing and evaluating a prototype conversational search. Futhermore, we developed and evaluated a system prototype, and considered technical issues for a conversational search system. The major achievements of this research include: (1) discovery of diverse search intents/tactics, (2) construction of a database of linguistic expressions of search intents/tactics, (3) identification of search intents/tactics that are difficult to predict, (4) construction of a prototype system, and (5) proposal of future technological issues.

Free Research Field

情報学

Academic Significance and Societal Importance of the Research Achievements

本研究では、従来研究されてきたキーワード検索方式において「無言」で行われてきたユーザと検索システムとのやりとりを検索方略に焦点を当てることで言語化できたことに学術的意義がある。また、言語化された検索方略のうち、言語表現から推定の容易な検索方略と困難な方略を解明できた点、検索方略分類器を実装することで会話検索のプロトタイプシステムの開発と評価を実現できた点も学術的意義がある。一方、近年生成系対話型AIが情報アクセスの一手段として急速に普及していく中で、検索方略というユーザ視点から会話検索システムの技術課題を明らかにできた点に社会的意義がある。

URL: 

Published: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi