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

Question Answering System for Numerical Data

Research Project

Project/Area Number 16K16120
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Intelligent informatics
Research InstitutionFUJITSU LABORATORIES LTD.

Principal Investigator

Yokono Hikaru  株式会社富士通研究所, その他部局等, 研究員(移行) (60535863)

Project Period (FY) 2016-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywords自然言語処理 / 意味解析 / コーパス構築 / 言語理解 / 人工知能 / 質問応答
Outline of Final Research Achievements

In this study, we aimed to develop a question answering system for numerical data, such as statistical information. Since some information obtained from numerical data can be obtained not only by referring the values stored in the data but also by calculating the value of the data such as the average, the question answering system for numerical data need the function to calculate the values in the data.
In order to develop a question answering system for such data, we constructed a dataset in which the correspondence between numerical data and linguistic expressions was manually annotated.
As a related study, in the machine reading task, we classify the intellectual processes required for the model, and analyze some datasets of the language understanding task based on that.

Academic Significance and Societal Importance of the Research Achievements

宣言的な知識が格納されたデータベースを知識源とするような一般的な質問応答システムでは質問に対する答えがデータベースに直接的に表現されているという仮定に基づいてモデルが構築される.一方で,数値データを対象とした質問応答システムでは,回答に必要な情報がデータ中に直接的に存在しておらず,回答のためにはデータ中の値を計算しなければならない,という状況が起こりうることを想定し,それらの計算のための機構を構築する必要がある.本研究ではその基礎となるデータセットの構築を行った.このデータセットを用いることで,言語表現による数値データの取り扱いに関する研究が行えると考えられる.

Report

(5 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (2 results)

All 2017

All Presentation (2 results) (of which Int'l Joint Research: 2 results)

  • [Presentation] Prerequisite Skills for Reading Comprehension: Multi-Perspective Analysis of MCTest Datasets and Systems2017

    • Author(s)
      Saku Sugawara, Hikaru Yokono, Akiko Aizawa
    • Organizer
      Thirty-First AAAI Conference on Artificial Intelligence
    • Place of Presentation
      Hilton San Francisco Union Square
    • Year and Date
      2017-02-04
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] Evaluation Metrics for Machine Reading Comprehension: Prerequisite Skills and Readability2017

    • Author(s)
      Saku Sugawara, Yusuke Kido, Hikaru Yokono and Akiko Aizawa
    • Organizer
      Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2016-04-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi