Edinburgh s phrase-based machine translation systems for WMT-14

Nadir Durrani; Barry Haddow; Philipp Koehn; Kenneth Heafield

Edinburgh s phrase-based machine translation systems for WMT-14

Nadir Durrani, Barry Haddow, Philipp Koehn, Kenneth Heafield

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

Abstract

This paper describes the University of Edinburgh s (UEDIN) phrase-based submissions to the translation and medical translation shared tasks of the 2014 Workshop on Statistical Machine Translation (WMT). We participated in all language pairs. We have improved upon our 2013 system by i) using generalized representations, specifically automatic word clusters for translations out of English, ii) using unsupervised character-based models to translate unknown words in Russian-English and Hindi-English pairs, iii) synthesizing Hindi data from closely-related Urdu data, and iv) building huge language on the common crawl corpus.

Original language	English
Title of host publication	ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	97-104
Number of pages	8
ISBN (Electronic)	9781941643174
Publication status	Published - 2014
Externally published	Yes
Event	9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Association for Computational Linguistics, ACL 2014 - Baltimore, United States Duration: 26 Jun 2014 → 27 Jun 2014

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Association for Computational Linguistics, ACL 2014
Country/Territory	United States
City	Baltimore
Period	26/06/14 → 27/06/14

Cite this

Durrani, N., Haddow, B., Koehn, P., & Heafield, K. (2014). Edinburgh s phrase-based machine translation systems for WMT-14. In ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop (pp. 97-104). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL).

Durrani, Nadir ; Haddow, Barry ; Koehn, Philipp et al. / Edinburgh s phrase-based machine translation systems for WMT-14. ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2014. pp. 97-104 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{48acf7d25fd44d72a0e95526cd08008c,

title = "Edinburgh s phrase-based machine translation systems for WMT-14",

abstract = "This paper describes the University of Edinburgh s (UEDIN) phrase-based submissions to the translation and medical translation shared tasks of the 2014 Workshop on Statistical Machine Translation (WMT). We participated in all language pairs. We have improved upon our 2013 system by i) using generalized representations, specifically automatic word clusters for translations out of English, ii) using unsupervised character-based models to translate unknown words in Russian-English and Hindi-English pairs, iii) synthesizing Hindi data from closely-related Urdu data, and iv) building huge language on the common crawl corpus.",

author = "Nadir Durrani and Barry Haddow and Philipp Koehn and Kenneth Heafield",

note = "Publisher Copyright: {\textcopyright} Proceedings of the Annual Meeting of the Association for Computational Linguistics 2014.; 9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Association for Computational Linguistics, ACL 2014 ; Conference date: 26-06-2014 Through 27-06-2014",

year = "2014",

language = "English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "97--104",

booktitle = "ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop",

address = "United States",

}

Durrani, N, Haddow, B, Koehn, P & Heafield, K 2014, Edinburgh s phrase-based machine translation systems for WMT-14. in ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 97-104, 9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Association for Computational Linguistics, ACL 2014, Baltimore, United States, 26/06/14.

Edinburgh s phrase-based machine translation systems for WMT-14. / Durrani, Nadir; Haddow, Barry; Koehn, Philipp et al.
ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2014. p. 97-104 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - Edinburgh s phrase-based machine translation systems for WMT-14

AU - Durrani, Nadir

AU - Haddow, Barry

AU - Koehn, Philipp

AU - Heafield, Kenneth

PY - 2014

Y1 - 2014

N2 - This paper describes the University of Edinburgh s (UEDIN) phrase-based submissions to the translation and medical translation shared tasks of the 2014 Workshop on Statistical Machine Translation (WMT). We participated in all language pairs. We have improved upon our 2013 system by i) using generalized representations, specifically automatic word clusters for translations out of English, ii) using unsupervised character-based models to translate unknown words in Russian-English and Hindi-English pairs, iii) synthesizing Hindi data from closely-related Urdu data, and iv) building huge language on the common crawl corpus.

AB - This paper describes the University of Edinburgh s (UEDIN) phrase-based submissions to the translation and medical translation shared tasks of the 2014 Workshop on Statistical Machine Translation (WMT). We participated in all language pairs. We have improved upon our 2013 system by i) using generalized representations, specifically automatic word clusters for translations out of English, ii) using unsupervised character-based models to translate unknown words in Russian-English and Hindi-English pairs, iii) synthesizing Hindi data from closely-related Urdu data, and iv) building huge language on the common crawl corpus.

UR - http://www.scopus.com/inward/record.url?scp=85122622861&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85122622861

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 97

EP - 104

BT - ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

T2 - 9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Association for Computational Linguistics, ACL 2014

Y2 - 26 June 2014 through 27 June 2014

ER -

Edinburgh s phrase-based machine translation systems for WMT-14

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this