EU-BRIDGE MT: Combined machine translation

Markus Freitag; Stephan Peitz; Joern Wuebker; Hermann Ney; Matthias Huck; Rico Sennrich; Nadir Durrani; Maria Nadejde; Philip Williams; Philipp Koehn; Teresa Herrmann; Eunah Cho; Alex Waibel

EU-BRIDGE MT: Combined machine translation

Markus Freitag, Stephan Peitz, Joern Wuebker, Hermann Ney, Matthias Huck, Rico Sennrich, Nadir Durrani, Maria Nadejde, Philip Williams, Philipp Koehn, Teresa Herrmann, Eunah Cho, Alex Waibel

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

13 Citations (Scopus)

Abstract

This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German!English and English!German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014). We combined up to nine different machine translation engines via system combination. RWTH Aachen University, the University of Edinburgh, and Karlsruhe Institute of Technology developed several individual systems which serve as system combination input. We devoted special attention to building syntax-based systems and combining them with the phrasebased ones. The joint setups yield empirical gains of up to 1.6 points in BLEU and 1.0 points in TER on the WMT newstest2013 test set compared to the best single systems.

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	105-113
Number of pages	9
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

Freitag, M., Peitz, S., Wuebker, J., Ney, H., Huck, M., Sennrich, R., Durrani, N., Nadejde, M., Williams, P., Koehn, P., Herrmann, T., Cho, E., & Waibel, A. (2014). EU-BRIDGE MT: Combined machine translation. In ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop (pp. 105-113). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL).

@inproceedings{76a36aac927c49fa892964f4676eb32d,

title = "EU-BRIDGE MT: Combined machine translation",

abstract = "This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German!English and English!German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014). We combined up to nine different machine translation engines via system combination. RWTH Aachen University, the University of Edinburgh, and Karlsruhe Institute of Technology developed several individual systems which serve as system combination input. We devoted special attention to building syntax-based systems and combining them with the phrasebased ones. The joint setups yield empirical gains of up to 1.6 points in BLEU and 1.0 points in TER on the WMT newstest2013 test set compared to the best single systems.",

author = "Markus Freitag and Stephan Peitz and Joern Wuebker and Hermann Ney and Matthias Huck and Rico Sennrich and Nadir Durrani and Maria Nadejde and Philip Williams and Philipp Koehn and Teresa Herrmann and Eunah Cho and Alex Waibel",

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 = "105--113",

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

address = "United States",

}

Freitag, M, Peitz, S, Wuebker, J, Ney, H, Huck, M, Sennrich, R, Durrani, N, Nadejde, M, Williams, P, Koehn, P, Herrmann, T, Cho, E & Waibel, A 2014, EU-BRIDGE MT: Combined machine translation. 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. 105-113, 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.

EU-BRIDGE MT: Combined machine translation. / Freitag, Markus; Peitz, Stephan; Wuebker, Joern et al.
ACL 2014 - 9th Workshop on Statistical Machine Translation, WMT 2014, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2014. p. 105-113 (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 - EU-BRIDGE MT

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

AU - Freitag, Markus

AU - Peitz, Stephan

AU - Wuebker, Joern

AU - Ney, Hermann

AU - Huck, Matthias

AU - Sennrich, Rico

AU - Durrani, Nadir

AU - Nadejde, Maria

AU - Williams, Philip

AU - Koehn, Philipp

AU - Herrmann, Teresa

AU - Cho, Eunah

AU - Waibel, Alex

PY - 2014

Y1 - 2014

N2 - This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German!English and English!German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014). We combined up to nine different machine translation engines via system combination. RWTH Aachen University, the University of Edinburgh, and Karlsruhe Institute of Technology developed several individual systems which serve as system combination input. We devoted special attention to building syntax-based systems and combining them with the phrasebased ones. The joint setups yield empirical gains of up to 1.6 points in BLEU and 1.0 points in TER on the WMT newstest2013 test set compared to the best single systems.

AB - This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German!English and English!German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014). We combined up to nine different machine translation engines via system combination. RWTH Aachen University, the University of Edinburgh, and Karlsruhe Institute of Technology developed several individual systems which serve as system combination input. We devoted special attention to building syntax-based systems and combining them with the phrasebased ones. The joint setups yield empirical gains of up to 1.6 points in BLEU and 1.0 points in TER on the WMT newstest2013 test set compared to the best single systems.

UR - https://www.scopus.com/pages/publications/84943747120

M3 - Conference contribution

AN - SCOPUS:84943747120

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

SP - 105

EP - 113

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

PB - Association for Computational Linguistics (ACL)

Y2 - 26 June 2014 through 27 June 2014

ER -

EU-BRIDGE MT: Combined machine translation

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this