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

Natural language generation of trend descriptions for pedagogic purposes

Research Project

Project/Area Number 22K00792
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 02100:Foreign language education-related
Research InstitutionThe University of Aizu

Principal Investigator

Blake John  会津大学, コンピュータ理工学部, 教授 (80635954)

Co-Investigator(Kenkyū-buntansha) Pyshkin Evgeny  会津大学, コンピュータ理工学部, 上級准教授 (50794088)
Project Period (FY) 2022-04-01 – 2025-03-31
Project Status Completed (Fiscal Year 2024)
Budget Amount *help
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2024: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2023: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
KeywordsIntelligent CALL / trend description / time-series description / describing trends / time series descriptions / written descriptions / scientific writing / academic writing / education technology / NLG / trend descriptions / describing graphs / intelligent CALL / data series description / NLP / language generation
Outline of Research at the Start

This interactive online tool provides unlimited practice opportunities to describe graphs and charts. Students can practice at three levels: word, clause or sentence using generated practice texts. Students either fill in the gaps, complete sentence stems or draft the whole text. On completion of their practice task, they compare their answers with an automatically generated plain or colorized exemplar text. This helps learners notice patterns, which is said to be a precursor to learning.

Outline of Final Research Achievements

We developed TrendScribe, an online tool that helps learners of English describe trends in graphs;an important skill for university admission and academic success. Users can upload data and receive model texts at six different language levels, from beginner to advanced. The system uses both rule-based methods and artificial intelligence (AI) to generate examples. Learners can also practice by comparing their own writing to the model texts. The tool was tested with university students, who reported it was helpful and easy to use. This research combines language learning and technology to support students preparing for tests like IELTS and TOEFL. Our work helps make data interpretation and academic writing more accessible to non-native English speakers.

Academic Significance and Societal Importance of the Research Achievements

Scientifically, this research contributes to natural language processing and language education. Socially, it supports inclusive learning by helping non-native speakers develop the skills needed to succeed in global academic and professional settings.

Report

(4 results)
  • 2024 Annual Research Report   Final Research Report ( PDF )
  • 2023 Research-status Report
  • 2022 Research-status Report
  • Research Products

    (8 results)

All 2025 2024 2022

All Journal Article (2 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 2 results) Presentation (6 results) (of which Int'l Joint Research: 1 results)

  • [Journal Article] TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English2025

    • Author(s)
      John Blake, Peng Zhao and Evgeny Pyshkin
    • Journal Title

      Multi-disciplinary Trends in Artificial Intelligence

      Volume: 1 Pages: 89-101

    • DOI

      10.1007/978-981-96-0692-4_8

    • ISBN
      9789819606917, 9789819606924
    • Related Report
      2024 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Bringing linguistics to a programming class: A problem of automatic text generation for desc2022

    • Author(s)
      Pyshkin, E. and Blake, J.
    • Journal Title

      New Trends in Intelligent Software Methodologies, Tools and Techniques

      Volume: 1 Pages: 621-630

    • DOI

      10.3233/faia220291

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English2024

    • Author(s)
      John Blake, Peng Zhao and Evgeny Pyshkin
    • Organizer
      Multi-disciplinary Trends in Artificial Intelligence (MIWAI 2025)
    • Related Report
      2024 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Personalizing practice with natural language generation2022

    • Author(s)
      Blake, J.
    • Organizer
      ELT Research in Action (ELTRIA) Conference
    • Related Report
      2022 Research-status Report
  • [Presentation] Intelligent CALL: Individualizing learning using natural language generation2022

    • Author(s)
      Blake, J.
    • Organizer
      HKAECT International Conference
    • Related Report
      2022 Research-status Report
  • [Presentation] Automatic generation of trend descriptions for language learning purposes: A pilot study2022

    • Author(s)
      Blake, J., Pyshkin, E. and Bogach, N.
    • Organizer
      International Conference on Open and Innovative Education
    • Related Report
      2022 Research-status Report
  • [Presentation] Bringing linguistics to a programming class: A problem of automatic text generation for describing data series2022

    • Author(s)
      Pyshkin, E. and Blake, J.
    • Organizer
      International Conference on Intelligent Software Methodologies, Tools, and Techniques
    • Related Report
      2022 Research-status Report
  • [Presentation] Trend description generation: Problem breakdown to principles to pseudocode to Python2022

    • Author(s)
      Blake, J., Tamura, K., Takeue, F., and Pyshkin, E.
    • Organizer
      International Conference on ICT Integration in Technical Education
    • Related Report
      2022 Research-status Report

URL: 

Published: 2022-04-19   Modified: 2026-01-16  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi