Statistical Machine Translation with Automatic Identification of Translationese

Naama Twitto-Shmuel; Noam Ordan; Shuly Wintner

doi:10.18653/v1/W15-3002

Statistical Machine Translation with Automatic Identification of Translationese

Naama Twitto-Shmuel, Noam Ordan, Shuly Wintner

Department of Computer Science

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

Abstract

Translated texts (in any language) are so markedly different from original ones that text classification techniques can be used to tease them apart. Previous work has shown that awareness to these differences can significantly improve statistical machine translation. These results, however, required meta-information on the ontological status of texts (original or translated) which is typically unavailable. In this work we show that the predictions of translationese classifiers are as good as meta-information. First, when a monolingual corpus in the target language is given, to be used for constructing a language
model, predicting the translated portions of the corpus, and using only them for the language model, is as good as using the entire corpus. Second, identifying the portions of a parallel corpus that are translated in the direction of the translation task, and using only them for the translation model, is as good as using the entire corpus. We present results from several language pairs
and various data sets, indicating that these results are robust and general.

Original language	English
Title of host publication	10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings
Editors	Ondrej Bojar, Rajan Chatterjee, Christian Federmann, Barry Haddow, Chris Hokamp, Matthias Huck, Varvara Logacheva, Pavel Pecina
Place of Publication	Lisbon, Portugal
Publisher	Association for Computational Linguistics (ACL)
Pages	47-57
Number of pages	11
ISBN (Electronic)	9781941643327
DOIs	https://doi.org/10.18653/v1/W15-3002
State	Published - 2015
Event	10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: 17 Sep 2015 → 18 Sep 2015

Publication series

Name	10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings

Conference

Conference	10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 18/09/15

Bibliographical note

Funding Information:
This research was supported by a grant from the Israeli Ministry of Science and Technology. The second author was supported by Cluster of Excellence MMCI at Saarland University. We are grateful to Gennadi Lembersky for his continuous help.

Publisher Copyright:
© EMNLP 2015. All rights reserved.

ASJC Scopus subject areas

Information Systems
Computational Theory and Mathematics
Computer Science Applications

Access to Document

10.18653/v1/W15-3002

https://aclanthology.org/W15-3002

Cite this

Twitto-Shmuel, N., Ordan, N., & Wintner, S. (2015). Statistical Machine Translation with Automatic Identification of Translationese. In O. Bojar, R. Chatterjee, C. Federmann, B. Haddow, C. Hokamp, M. Huck, V. Logacheva, & P. Pecina (Eds.), 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings (pp. 47-57). (10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/W15-3002

Twitto-Shmuel, Naama ; Ordan, Noam ; Wintner, Shuly. / Statistical Machine Translation with Automatic Identification of Translationese. 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings. editor / Ondrej Bojar ; Rajan Chatterjee ; Christian Federmann ; Barry Haddow ; Chris Hokamp ; Matthias Huck ; Varvara Logacheva ; Pavel Pecina. Lisbon, Portugal : Association for Computational Linguistics (ACL), 2015. pp. 47-57 (10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings).

@inproceedings{50d4f3a6a8194caca290fba5c3a31463,

title = "Statistical Machine Translation with Automatic Identification of Translationese",

abstract = "Translated texts (in any language) are so markedly different from original ones that text classification techniques can be used to tease them apart. Previous work has shown that awareness to these differences can significantly improve statistical machine translation. These results, however, required meta-information on the ontological status of texts (original or translated) which is typically unavailable. In this work we show that the predictions of translationese classifiers are as good as meta-information. First, when a monolingual corpus in the target language is given, to be used for constructing a languagemodel, predicting the translated portions of the corpus, and using only them for the language model, is as good as using the entire corpus. Second, identifying the portions of a parallel corpus that are translated in the direction of the translation task, and using only them for the translation model, is as good as using the entire corpus. We present results from several language pairsand various data sets, indicating that these results are robust and general.",

author = "Naama Twitto-Shmuel and Noam Ordan and Shuly Wintner",

note = "Publisher Copyright: {\textcopyright} EMNLP 2015. All rights reserved.; 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 17-09-2015 Through 18-09-2015",

year = "2015",

doi = "10.18653/v1/W15-3002",

language = "אנגלית",

series = "10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings",

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

pages = "47--57",

editor = "Ondrej Bojar and Rajan Chatterjee and Christian Federmann and Barry Haddow and Chris Hokamp and Matthias Huck and Varvara Logacheva and Pavel Pecina",

booktitle = "10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings",

address = "ארצות הברית",

}

Twitto-Shmuel, N, Ordan, N & Wintner, S 2015, Statistical Machine Translation with Automatic Identification of Translationese. in O Bojar, R Chatterjee, C Federmann, B Haddow, C Hokamp, M Huck, V Logacheva & P Pecina (eds), 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings. 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings, Association for Computational Linguistics (ACL), Lisbon, Portugal, pp. 47-57, 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17/09/15. https://doi.org/10.18653/v1/W15-3002

Statistical Machine Translation with Automatic Identification of Translationese. / Twitto-Shmuel, Naama; Ordan, Noam; Wintner, Shuly.
10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings. ed. / Ondrej Bojar; Rajan Chatterjee; Christian Federmann; Barry Haddow; Chris Hokamp; Matthias Huck; Varvara Logacheva; Pavel Pecina. Lisbon, Portugal: Association for Computational Linguistics (ACL), 2015. p. 47-57 (10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings).

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

TY - GEN

T1 - Statistical Machine Translation with Automatic Identification of Translationese

AU - Twitto-Shmuel, Naama

AU - Ordan, Noam

AU - Wintner, Shuly

PY - 2015

Y1 - 2015

N2 - Translated texts (in any language) are so markedly different from original ones that text classification techniques can be used to tease them apart. Previous work has shown that awareness to these differences can significantly improve statistical machine translation. These results, however, required meta-information on the ontological status of texts (original or translated) which is typically unavailable. In this work we show that the predictions of translationese classifiers are as good as meta-information. First, when a monolingual corpus in the target language is given, to be used for constructing a languagemodel, predicting the translated portions of the corpus, and using only them for the language model, is as good as using the entire corpus. Second, identifying the portions of a parallel corpus that are translated in the direction of the translation task, and using only them for the translation model, is as good as using the entire corpus. We present results from several language pairsand various data sets, indicating that these results are robust and general.

AB - Translated texts (in any language) are so markedly different from original ones that text classification techniques can be used to tease them apart. Previous work has shown that awareness to these differences can significantly improve statistical machine translation. These results, however, required meta-information on the ontological status of texts (original or translated) which is typically unavailable. In this work we show that the predictions of translationese classifiers are as good as meta-information. First, when a monolingual corpus in the target language is given, to be used for constructing a languagemodel, predicting the translated portions of the corpus, and using only them for the language model, is as good as using the entire corpus. Second, identifying the portions of a parallel corpus that are translated in the direction of the translation task, and using only them for the translation model, is as good as using the entire corpus. We present results from several language pairsand various data sets, indicating that these results are robust and general.

UR - http://www.scopus.com/inward/record.url?scp=85025160155&partnerID=8YFLogxK

U2 - 10.18653/v1/W15-3002

DO - 10.18653/v1/W15-3002

M3 - פרסום בספר כנס

T3 - 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings

SP - 47

EP - 57

BT - 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings

A2 - Bojar, Ondrej

A2 - Chatterjee, Rajan

A2 - Federmann, Christian

A2 - Haddow, Barry

A2 - Hokamp, Chris

A2 - Huck, Matthias

A2 - Logacheva, Varvara

A2 - Pecina, Pavel

PB - Association for Computational Linguistics (ACL)

CY - Lisbon, Portugal

T2 - 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015

Y2 - 17 September 2015 through 18 September 2015

ER -

Twitto-Shmuel N, Ordan N, Wintner S. Statistical Machine Translation with Automatic Identification of Translationese. In Bojar O, Chatterjee R, Federmann C, Haddow B, Hokamp C, Huck M, Logacheva V, Pecina P, editors, 10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings. Lisbon, Portugal: Association for Computational Linguistics (ACL). 2015. p. 47-57. (10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Proceedings). doi: 10.18653/v1/W15-3002

Statistical Machine Translation with Automatic Identification of Translationese

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this