• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2021 年度 実績報告書

英語学習者のための議論構造を考慮した作文支援システム

研究課題

研究課題/領域番号 20J13239
研究機関東京工業大学

研究代表者

PUTRA JAN WIRA GOTAMA  東京工業大学, 情報理工学院, 特別研究員(DC2)

研究期間 (年度) 2020-04-24 – 2022-03-31
キーワードArgumentative Structure / EFL learners / ICNALE-AS2R Corpus / Annotation / Sentence Reordering / Structure Parsing
研究実績の概要

My research aims to develop a support tool for analysis and improving argumentative essays written by English-as-foreign-language (EFL) learners. The tool extracts and visualizes the argumentative structure of a given essay, and then suggests an improved version of the essay by reordering sentences. This project was divided into several steps:
(a) Dataset Construction. In 2020, I constructed the first corpus of 434 essays written by EFL learners (ICNALE-AS2R), which have been annotated with argumentative structure and sentence reordering. I also developed an in-house annotation software (open-source) TIARA for this step.
(b) Structure Parsing Model. Given an input essay, I developed a deep learning system to predict the argumentative structure of the essay. I used the combination of Biaffine Attention and BERT models. I also proposed multi-task and multi-corpora training strategies which enhanced the parsing performance of the base model. The idea was to guide the model on how to reduce the search space and to utilise existing non-EFL datasets via selective sampling.
(c) Sentence Reordering Model. Given an essay and its corresponding argumentative structure as input, I proposed a reordering system based on the linguistic theory of coherence. The task was formulated as a traversal problem, containing two steps. The first is a pairwise ordering constraint task between pairs of sentences (tackled using ALBERT model). The second is a traversal (output generation) step using an ad-hoc algorithm. Detailed empirical evaluation showed that my proposed system has a good potential.

現在までの達成度 (段落)

令和3年度が最終年度であるため、記入しない。

今後の研究の推進方策

令和3年度が最終年度であるため、記入しない。

備考

BEA and ArgMin are peer-reviewed international conference papers

  • 研究成果

    (9件)

すべて 2021 その他

すべて 国際共同研究 (1件) 雑誌論文 (2件) (うち国際共著 2件、 査読あり 2件、 オープンアクセス 2件) 学会発表 (2件) (うち国際学会 2件) 備考 (4件)

  • [国際共同研究] University of Cambridge(英国)

    • 国名
      英国
    • 外国機関名
      University of Cambridge
  • [雑誌論文] Annotating argumentative structure in English-as-a-Foreign-Language learner essays2021

    • 著者名/発表者名
      Jan Wira Gotama Putra, Simone Teufel and Takenobu Tokunaga
    • 雑誌名

      Natural Language Engineering

      巻: - ページ: 1-27

    • DOI

      10.1017/S1351324921000218

    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] TIARA 2.0: an interactive tool for annotating discourse structure and text improvement2021

    • 著者名/発表者名
      Jan Wira Gotama Putra, Kana Matsumura, Simone Teufel and Takenobu Tokunaga
    • 雑誌名

      Language Resources & Evaluation

      巻: - ページ: 1-25

    • DOI

      10.1007/s10579-021-09566-0

    • 査読あり / オープンアクセス / 国際共著
  • [学会発表] Parsing Argumentative Structure in English-as-Foreign-Language Essays2021

    • 著者名/発表者名
      Jan Wira Gotama Putra
    • 学会等名
      Sixteenth Workshop on Innovative Use of NLP for Building Educational Applications (BEA), Association for Computational Linguistics
    • 国際学会
  • [学会発表] Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance2021

    • 著者名/発表者名
      Jan Wira Gotama Putra
    • 学会等名
      Eighth Workshop on Argument Mining (ArgMin), Association for Computational Linguistics
    • 国際学会
  • [備考] TIARA homepage

    • URL

      https://sites.google.com/view/tokyotechcl-tiara/

  • [備考] ICNALE-AS2R dataset

    • URL

      https://www.gsk.or.jp/en/catalog/gsk2021-a

  • [備考] Released code for BEA paper

    • URL

      https://github.com/wiragotama/BEA2021

  • [備考] Released code for ArgMin paper

    • URL

      https://github.com/wiragotama/ArgMin2021

URL: 

公開日: 2022-12-28  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi