Supporting content evaluation of student summaries by idea unit embedding

Marcello Gecchele, Hiroaki Yamada, Takenobu Tokunaga, Yasuyo Sawaki

研究成果: Conference contribution

抄録

This paper discusses the computer-assisted content evaluation of summaries. We propose a method to make a correspondence between the segments of the source text and its summary. As a unit of the segment, we adopt "Idea Unit (IU)" which is proposed in Applied Linguistics. Introducing IUs enables us to make a correspondence even for the sentences that contain multiple ideas. The IU correspondence is made based on the similarity between vector representations of IU. An evaluation experiment with two source texts and 20 summaries showed that the proposed method is more robust against rephrased expressions than the conventional ROUGEbased baselines. Also, the proposed method outperformed the baselines in recall. We implemented the proposed method in a GUI tool "Segment Matcher" that aids teachers to establish a link between corresponding IUs across the summary and source text.

本文言語English
ホスト出版物のタイトルACL 2019 - Innovative Use of NLP for Building Educational Applications, BEA 2019 - Proceedings of the 14th Workshop
出版社Association for Computational Linguistics (ACL)
ページ343-348
ページ数6
ISBN(電子版)9781950737345
出版ステータスPublished - 2019
イベント14th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2019, collocated with ACL 2019 - Florence, Italy
継続期間: 2019 8月 2 → …

出版物シリーズ

名前ACL 2019 - Innovative Use of NLP for Building Educational Applications, BEA 2019 - Proceedings of the 14th Workshop

Conference

Conference14th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2019, collocated with ACL 2019
国/地域Italy
CityFlorence
Period19/8/2 → …

ASJC Scopus subject areas

  • 言語および言語学
  • 言語学および言語
  • ソフトウェア

フィンガープリント

「Supporting content evaluation of student summaries by idea unit embedding」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル