Incremental methods to select test sentences for evaluating translation ability

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004
PublisherEuropean Language Resources Association (ELRA)
Pages2015-2018
Number of pages4
ISBN (Electronic)2951740816, 9782951740815
Publication statusPublished - 2004 Jan 1
Externally publishedYes
Event4th International Conference on Language Resources and Evaluation, LREC 2004 - Lisbon, Portugal
Duration: 2004 May 262004 May 28

Other

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

Fingerprint

ability
programming
language
Test Methods
Correlation Coefficient
Programming
Language

ASJC Scopus subject areas

  • Library and Information Sciences
  • Education
  • Language and Linguistics
  • Linguistics and Language

Cite this

Akiba, Y., Sumita, E., Nakaiwa, H., Yamamoto, S., & Okuno, H. G. (2004). Incremental methods to select test sentences for evaluating translation ability. In Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004 (pp. 2015-2018). European Language Resources Association (ELRA).

Incremental methods to select test sentences for evaluating translation ability. / Akiba, Yasuhiro; Sumita, Eiichiro; Nakaiwa, Hiromi; Yamamoto, Seiichi; Okuno, Hiroshi G.

Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. European Language Resources Association (ELRA), 2004. p. 2015-2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Akiba, Y, Sumita, E, Nakaiwa, H, Yamamoto, S & Okuno, HG 2004, Incremental methods to select test sentences for evaluating translation ability. in Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. European Language Resources Association (ELRA), pp. 2015-2018, 4th International Conference on Language Resources and Evaluation, LREC 2004, Lisbon, Portugal, 04/5/26.
Akiba Y, Sumita E, Nakaiwa H, Yamamoto S, Okuno HG. Incremental methods to select test sentences for evaluating translation ability. In Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. European Language Resources Association (ELRA). 2004. p. 2015-2018
Akiba, Yasuhiro ; Sumita, Eiichiro ; Nakaiwa, Hiromi ; Yamamoto, Seiichi ; Okuno, Hiroshi G. / Incremental methods to select test sentences for evaluating translation ability. Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. European Language Resources Association (ELRA), 2004. pp. 2015-2018
@inproceedings{ac8472ee6dfb4541b7061c0140cc4f6e,
title = "Incremental methods to select test sentences for evaluating translation ability",
abstract = "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.",
author = "Yasuhiro Akiba and Eiichiro Sumita and Hiromi Nakaiwa and Seiichi Yamamoto and Okuno, {Hiroshi G.}",
year = "2004",
month = "1",
day = "1",
language = "English",
pages = "2015--2018",
booktitle = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",
publisher = "European Language Resources Association (ELRA)",

}

TY - GEN

T1 - Incremental methods to select test sentences for evaluating translation ability

AU - Akiba, Yasuhiro

AU - Sumita, Eiichiro

AU - Nakaiwa, Hiromi

AU - Yamamoto, Seiichi

AU - Okuno, Hiroshi G.

PY - 2004/1/1

Y1 - 2004/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85037092366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037092366&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85037092366

SP - 2015

EP - 2018

BT - Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004

PB - European Language Resources Association (ELRA)

ER -