Translation errors from English to Portuguese: an annotated corpus

Ângela Costa; Tiago Luís; Luísa Coheur

Translation errors from English to Portuguese: an annotated corpus

Ângela Costa, Tiago Luís, Luísa Coheur

Centro de Linguística da UNL (CLUNL)

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

28 Downloads (Pure)

Abstract

Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google’s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.

Original language	English
Title of host publication	Proceedings of the Ninth International Conference on Language Resources and Evaluation
Editors	Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Place of Publication	Reykjavik
Publisher	ELRA
Pages	1231-1234
Number of pages	4
ISBN (Print)	978-2-9517408-8-4
Publication status	Published - 2014
Event	LREC 2014 - The 9th International Conference on Language Resources and Evaluation - Reykjavik, Iceland Duration: 26 May 2014 → 31 May 2014 http://lrec2014.lrec-conf.org/en/

Conference

Conference	LREC 2014 - The 9th International Conference on Language Resources and Evaluation
Abbreviated title	LREC 2014
Country/Territory	Iceland
City	Reykjavik
Period	26/05/14 → 31/05/14
Internet address	http://lrec2014.lrec-conf.org/en/

Keywords

Error Analysis
Machine Translation
Evaluation Methodologies

Access to Document

Translation errors from English to Portuguese an annotated corpusFinal published version, 408 KBLicence: CC BY-NC

http://www.lrec-conf.org/proceedings/lrec2014/summaries/199.htmlLicence: CC BY-NC

Cite this

Costa, Â., Luís, T., & Coheur, L. (2014). Translation errors from English to Portuguese: an annotated corpus. In N. Calzolari, K. Choukri, T. Declerck, H. Loftsson, B. Maegaard, J. Mariani, A. Moreno, J. Odijk, & S. Piperidis (Eds.), Proceedings of the Ninth International Conference on Language Resources and Evaluation (pp. 1231-1234). ELRA. http://www.lrec-conf.org/proceedings/lrec2014/summaries/199.html

Costa, Ângela ; Luís, Tiago ; Coheur, Luísa. / Translation errors from English to Portuguese : an annotated corpus. Proceedings of the Ninth International Conference on Language Resources and Evaluation. editor / Nicoletta Calzolari ; Khalid Choukri ; Thierry Declerck ; Hrafn Loftsson ; Bente Maegaard ; Joseph Mariani ; Asuncion Moreno ; Jan Odijk ; Stelios Piperidis. Reykjavik : ELRA, 2014. pp. 1231-1234

@inproceedings{aa7a4434b0524b058b5d2a9686493e65,

title = "Translation errors from English to Portuguese: an annotated corpus",

abstract = "Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google{\textquoteright}s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors. ",

keywords = "Error Analysis, Machine Translation, Evaluation Methodologies",

author = "{\^A}ngela Costa and Tiago Lu{\'i}s and Lu{\'i}sa Coheur",

note = "info:eu-repo/grantAgreement/FCT/3599-PPCDT/133002/PT# info:eu-repo/grantAgreement/FCT/SFRH/SFRH%2FBD%2F85737%2F2012/PT# PEst-OE/EEI/LA0021/2013 SFRH/BD/85737/2012; LREC 2014 - The 9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",

year = "2014",

language = "English",

isbn = "978-2-9517408-8-4",

pages = "1231--1234",

editor = "Nicoletta Calzolari and Choukri, {Khalid } and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis",

booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation",

publisher = "ELRA",

url = "http://lrec2014.lrec-conf.org/en/",

}

Costa, Â, Luís, T & Coheur, L 2014, Translation errors from English to Portuguese: an annotated corpus. in N Calzolari, K Choukri, T Declerck, H Loftsson, B Maegaard, J Mariani, A Moreno, J Odijk & S Piperidis (eds), Proceedings of the Ninth International Conference on Language Resources and Evaluation. ELRA, Reykjavik, pp. 1231-1234, LREC 2014 - The 9th International Conference on Language Resources and Evaluation, Reykjavik, Iceland, 26/05/14. <http://www.lrec-conf.org/proceedings/lrec2014/summaries/199.html>

Translation errors from English to Portuguese: an annotated corpus. / Costa, Ângela; Luís, Tiago; Coheur, Luísa.
Proceedings of the Ninth International Conference on Language Resources and Evaluation. ed. / Nicoletta Calzolari; Khalid Choukri; Thierry Declerck; Hrafn Loftsson; Bente Maegaard; Joseph Mariani; Asuncion Moreno; Jan Odijk; Stelios Piperidis. Reykjavik: ELRA, 2014. p. 1231-1234.

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

TY - GEN

T1 - Translation errors from English to Portuguese

T2 - LREC 2014 - The 9th International Conference on Language Resources and Evaluation

AU - Costa, Ângela

AU - Luís, Tiago

AU - Coheur, Luísa

N1 - info:eu-repo/grantAgreement/FCT/3599-PPCDT/133002/PT# info:eu-repo/grantAgreement/FCT/SFRH/SFRH%2FBD%2F85737%2F2012/PT# PEst-OE/EEI/LA0021/2013 SFRH/BD/85737/2012

PY - 2014

Y1 - 2014

N2 - Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google’s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.

AB - Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google’s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.

KW - Error Analysis

KW - Machine Translation

KW - Evaluation Methodologies

M3 - Conference contribution

SN - 978-2-9517408-8-4

SP - 1231

EP - 1234

BT - Proceedings of the Ninth International Conference on Language Resources and Evaluation

A2 - Calzolari, Nicoletta

A2 - Choukri, Khalid

A2 - Declerck, Thierry

A2 - Loftsson, Hrafn

A2 - Maegaard, Bente

A2 - Mariani, Joseph

A2 - Moreno, Asuncion

A2 - Odijk, Jan

A2 - Piperidis, Stelios

PB - ELRA

CY - Reykjavik

Y2 - 26 May 2014 through 31 May 2014

ER -

Translation errors from English to Portuguese: an annotated corpus

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this