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

Interactive Summarization System to Support Literature Survey

Research Project

Project/Area Number 16K12546
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Library and information science/Humanistic social informatics
Research InstitutionNational Institute of Informatics

Principal Investigator

Aizawa Akiko  国立情報学研究所, コンテンツ科学研究系, 教授 (90222447)

Co-Investigator(Kenkyū-buntansha) 徳永 健伸  東京工業大学, 情報理工学院, 教授 (20197875)
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords情報組織化 / レビューマトリックス / 文書要約 / 質問応答システム / 文検索
Outline of Final Research Achievements

Scientific literature survey is time-consuming and difficult for researchers and engineers who need to grasp the trends of specific research topics. In many cases, necessary information is not written in the abstracts, and users are enforced to read through the entire papers. One of the conventional practices is to generate a review matrix that organizes the information-in-need in a table format. This research aims at supporting the users’ creation of review matrices. In our study, we developed a method for automatically summarizing multiple articles for a given query. We also constructed a dataset for evaluation and verified the effectiveness of the proposed method.

Academic Significance and Societal Importance of the Research Achievements

ユーザの理解支援の研究においては、自動評価が容易に行えるタスクの設計が研究の重要な手段となる。本研究では、レビューマトリックスの作成というタスクを設定することで効率的にデータセットが作成できることを示した。また、支援に必要となる要素技術として自動要約や機械読解の先端技術の研究に取り組み、当該タスクにおける有効性を示した。

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (6 results)

All 2018 2017 2016

All Presentation (6 results) (of which Int'l Joint Research: 6 results)

  • [Presentation] Query-focused Scientific Paper Summarization with Localized Sentence Representation.2018

    • Author(s)
      Kazutoshi Shinoda, Akiko Aizawa
    • Organizer
      The 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018), workshop at ACM SIGIR 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Evaluation Metrics for Machine Reading Comprehension: Prerequisite Skills and Readability.2017

    • Author(s)
      Saku Sugawara , Yusuke Kido , Hikaru Yokono, Akiko Aizawa
    • Organizer
      The 55th annual meeting of the Association for Computational Linguistics (ACL 2017)
    • Place of Presentation
      Vancouver, Canada
    • Year and Date
      2017-07-30
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Conditional Variational Framework for Dialog Generation.2017

    • Author(s)
      Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
    • Organizer
      The 55th annual meeting of the Association for Computational Linguistics (ACL 2017)
    • Place of Presentation
      Vancouver, Canada
    • Year and Date
      2017-07-30
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] Automatic Generation of Review Matrices as Multi-document Summarization of Scientific Papers.2017

    • Author(s)
      Hayato Hashimoto, Kazutoshi Shinoda, Hikaru Yokono, Akiko Aizawa
    • Organizer
      Second International Workshop on SCIentific DOCument Analysis (SCIDOCA 2017), associated with JSAI International Symposia on AI 2017 (IsAI-2017)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Automatic Generation of Review Matrices as Multi-document Summarization of Scientic Papers.2017

    • Author(s)
      Hayato Hashimoto, Kazutoshi Shinoda, Hikaru Yokono, Akiko Aizawa
    • Organizer
      BIRNDL’17: Bibliometric-enhanced IR and NLP for Digital Libraries, workshop at SIGIR 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Exploiting Synonymy and Hypernymy to Learn Efficient Meaning Representations.2016

    • Author(s)
      Thomas Perianin, Hajime Senuma, Akiko Aizawa
    • Organizer
      The 18th International Conference on Asia-Pacific Digital Libraries (ICADL 2016)
    • Place of Presentation
      Tsukuba, Japan
    • Year and Date
      2016-12-07
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi