Refinements to Interactive Translation Prediction Based on Search Graphs

Philipp Koehn; Chara Tsoukala; Herve Saint-Amand

Refinements to Interactive Translation Prediction Based on Search Graphs

Philipp Koehn, Chara Tsoukala, Herve Saint-Amand

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a number of refinements to the canonical approach to interactive translation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and letter prediction accuracy (+9.3%).

Original language	English
Title of host publication	Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers
Publisher	Association for Computational Linguistics
Pages	574-578
Number of pages	5
Publication status	Published - Jun 2014

Access to Document

Koehn_Koehn2014 Refinements to Interactive Translation PredictionFinal published version, 149 KB

http://aclweb.org/anthology/P/P14/P14-2094.pdf

CASMACAT- 'Congnitive Analysis and Statistical Methods for Advanced Computer Aided Translation'
Koehn, P. (Principal Investigator)
EU government bodies
1/11/11 → 31/10/14
Project: Research
CASMACAT - 'Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation'
Koehn, P. (Principal Investigator)
EU government bodies
1/11/11 → 31/10/14
Project: Research
CASMACAT
Koehn, P. (Principal Investigator)
EU government bodies
1/11/11 → 31/10/14
Project: Research

Cite this

Koehn, P., Tsoukala, C., & Saint-Amand, H. (2014). Refinements to Interactive Translation Prediction Based on Search Graphs. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers (pp. 574-578). Association for Computational Linguistics. http://aclweb.org/anthology/P/P14/P14-2094.pdf

@inproceedings{e8c09b2dab054f069f4ed1b2c841d040,

title = "Refinements to Interactive Translation Prediction Based on Search Graphs",

abstract = "We propose a number of refinements to the canonical approach to interactive translation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and letter prediction accuracy (+9.3%).",

author = "Philipp Koehn and Chara Tsoukala and Herve Saint-Amand",

year = "2014",

month = jun,

language = "English",

pages = "574--578",

booktitle = "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers",

publisher = "Association for Computational Linguistics",

}

Koehn, P, Tsoukala, C & Saint-Amand, H 2014, Refinements to Interactive Translation Prediction Based on Search Graphs. in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers. Association for Computational Linguistics, pp. 574-578. <http://aclweb.org/anthology/P/P14/P14-2094.pdf>

Refinements to Interactive Translation Prediction Based on Search Graphs. / Koehn, Philipp; Tsoukala, Chara; Saint-Amand, Herve.
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers. Association for Computational Linguistics, 2014. p. 574-578.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Refinements to Interactive Translation Prediction Based on Search Graphs

AU - Koehn, Philipp

AU - Tsoukala, Chara

AU - Saint-Amand, Herve

PY - 2014/6

Y1 - 2014/6

N2 - We propose a number of refinements to the canonical approach to interactive translation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and letter prediction accuracy (+9.3%).

AB - We propose a number of refinements to the canonical approach to interactive translation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and letter prediction accuracy (+9.3%).

M3 - Conference contribution

SP - 574

EP - 578

BT - Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 2: Short Papers

PB - Association for Computational Linguistics

ER -

Refinements to Interactive Translation Prediction Based on Search Graphs

Abstract

Access to Document

Fingerprint

Projects

CASMACAT- 'Congnitive Analysis and Statistical Methods for Advanced Computer Aided Translation'

CASMACAT - 'Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation'

CASMACAT

Cite this