Incremental methods to select test sentences for evaluating translation ability

Yasuhiro Akiba, Eiichiro Sumita, Hiromi Nakaiwa, Seiichi Yamamoto, Hiroshi G. Okuno

研究成果: Conference contribution

抄録

This paper addresses the problem of selecting test sentences for automatically evaluating language learners' translation ability within a smaller error. In this paper, the ability to translate is measured as a TOEIC score. The existing selection methods only check whether an individual test sentence contributes to the estimation of the ability to translate or that of more general academic abilities, although combinations of test sentences may be used to contribute the estimation. This paper proposes two methods that solve the selection problem. The first method selects test sentences to minimize the estimation errors of learners' TOEIC scores. The second method selects test sentences to maximize the correlation coefficient between the number of correct translations and learners' estimated TOEIC scores. The optimization technique used in both of the proposed methods is the gradient technique in mathematical programming. The proposed methods proved to be more accurate than any of the existing methods we tested, and they estimated each TOEIC score within a permissible error of 69 points.

本文言語English
ホスト出版物のタイトルProceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004
出版社European Language Resources Association (ELRA)
ページ2015-2018
ページ数4
ISBN(電子版)2951740816, 9782951740815
出版ステータスPublished - 2004 1月 1
外部発表はい
イベント4th International Conference on Language Resources and Evaluation, LREC 2004 - Lisbon, Portugal
継続期間: 2004 5月 262004 5月 28

Other

Other4th International Conference on Language Resources and Evaluation, LREC 2004
国/地域Portugal
CityLisbon
Period04/5/2604/5/28

ASJC Scopus subject areas

  • 図書館情報学
  • 教育
  • 言語および言語学
  • 言語学および言語

フィンガープリント

「Incremental methods to select test sentences for evaluating translation ability」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