Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment

Marine Carpuat; Yuval Marton; Nizar Habash

Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment

Marine Carpuat, Yuval Marton, Nizar Habash

Computer Science

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

Abstract

We study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT).We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difficult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. We therefore propose to reorder VS constructions into SV order for SMT word alignment only. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline and despite noisy parses.

Original language	English (US)
Title of host publication	ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages	178-183
Number of pages	6
State	Published - 2010
Event	48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden Duration: Jul 11 2010 → Jul 16 2010

Publication series

Name	ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Other

Other	48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
Country/Territory	Sweden
City	Uppsala
Period	7/11/10 → 7/16/10

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

Carpuat, M., Marton, Y., & Habash, N. (2010). Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 178-183). (ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment. / Carpuat, Marine; Marton, Yuval; Habash, Nizar.
ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 178-183 (ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

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

Carpuat, M, Marton, Y & Habash, N 2010, Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment. in ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, pp. 178-183, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 7/11/10.

Carpuat M, Marton Y, Habash N. Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 178-183. (ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Carpuat, Marine ; Marton, Yuval ; Habash, Nizar. / Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. pp. 178-183 (ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{36a65e3e682c4252a18b2f7dab53a015,

title = "Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment",

abstract = "We study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT).We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difficult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. We therefore propose to reorder VS constructions into SV order for SMT word alignment only. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline and despite noisy parses.",

author = "Marine Carpuat and Yuval Marton and Nizar Habash",

year = "2010",

language = "English (US)",

isbn = "9781617388088",

series = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

pages = "178--183",

booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

note = "48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 ; Conference date: 11-07-2010 Through 16-07-2010",

}

TY - GEN

T1 - Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment

AU - Carpuat, Marine

AU - Marton, Yuval

AU - Habash, Nizar

PY - 2010

Y1 - 2010

N2 - We study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT).We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difficult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. We therefore propose to reorder VS constructions into SV order for SMT word alignment only. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline and despite noisy parses.

AB - We study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT).We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difficult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. We therefore propose to reorder VS constructions into SV order for SMT word alignment only. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline and despite noisy parses.

UR - http://www.scopus.com/inward/record.url?scp=84859945878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859945878&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84859945878

SN - 9781617388088

T3 - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 178

EP - 183

BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

T2 - 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010

Y2 - 11 July 2010 through 16 July 2010

ER -

Improving Arabic-to-English Statistical Machine Translation by reordering post-verbal subjects for alignment

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this