Continuous Adaptation to User Feedback for Statistical Machine Translation

Frédéric Blain; Fethi Bougares; Amir Hazem; Loïc Barrault; Holger Schwenk

doi:10.3115/v1/n15-1103

Continuous Adaptation to User Feedback for Statistical Machine Translation

Frédéric Blain, Fethi Bougares, Amir Hazem, Loïc Barrault, Holger Schwenk

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain data. The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool. We analyze the influence of these adaptations on the translator productivity and on the overall post-editing effort. We show that significant improvements can be obtained by using the presented adaptation techniques.

Original language	English
Title of host publication	Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher	Association for Computational Linguistics
Pages	1001-1005
Number of pages	5
DOIs	https://doi.org/10.3115/v1/n15-1103
Publication status	Published - 2015
Externally published	Yes

Access to Document

10.3115/v1/n15-1103

http://www.aclweb.org/anthology/N15-1103

Cite this

Blain, F., Bougares, F., Hazem, A., Barrault, L., & Schwenk, H. (2015). Continuous Adaptation to User Feedback for Statistical Machine Translation. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 1001-1005). Association for Computational Linguistics. https://doi.org/10.3115/v1/n15-1103

@inproceedings{dcc67b8884be47819856f4f103cdddf0,

title = "Continuous Adaptation to User Feedback for Statistical Machine Translation",

abstract = "This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain data. The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool. We analyze the influence of these adaptations on the translator productivity and on the overall post-editing effort. We show that significant improvements can be obtained by using the presented adaptation techniques.",

author = "Fr{\'e}d{\'e}ric Blain and Fethi Bougares and Amir Hazem and Lo{\"i}c Barrault and Holger Schwenk",

year = "2015",

doi = "10.3115/v1/n15-1103",

language = "English",

pages = "1001--1005",

booktitle = "Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

publisher = "Association for Computational Linguistics",

}

Blain, F, Bougares, F, Hazem, A, Barrault, L & Schwenk, H 2015, Continuous Adaptation to User Feedback for Statistical Machine Translation. in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pp. 1001-1005. https://doi.org/10.3115/v1/n15-1103

Continuous Adaptation to User Feedback for Statistical Machine Translation. / Blain, Frédéric; Bougares, Fethi; Hazem, Amir et al.
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 2015. p. 1001-1005.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Continuous Adaptation to User Feedback for Statistical Machine Translation

AU - Blain, Frédéric

AU - Bougares, Fethi

AU - Hazem, Amir

AU - Barrault, Loïc

AU - Schwenk, Holger

PY - 2015

Y1 - 2015

N2 - This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain data. The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool. We analyze the influence of these adaptations on the translator productivity and on the overall post-editing effort. We show that significant improvements can be obtained by using the presented adaptation techniques.

AB - This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain data. The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool. We analyze the influence of these adaptations on the translator productivity and on the overall post-editing effort. We show that significant improvements can be obtained by using the presented adaptation techniques.

U2 - 10.3115/v1/n15-1103

DO - 10.3115/v1/n15-1103

M3 - Conference contribution

SP - 1001

EP - 1005

BT - Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

ER -

Continuous Adaptation to User Feedback for Statistical Machine Translation

Abstract

Access to Document

Fingerprint

Cite this