Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology

Justus Brockmann; Claudia Karin Wiesinger; Dragos Ioan Ciobanu

Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology

Department for Translation Studies

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

Abstract

As post-editing of machine translation (PEMT) is becoming one of the most dominant services offered by the language services industry (LSI), efforts are being made to support provision of this service with additional technology. We present text-to-speech (T2S) as a potential attention-raising technology for post-editors. Our study was conducted with university students and included both PEMT and error annotation of a creative text with and without T2S. Focusing on the error annotation data, our analysis finds that participants under-annotated fewer MT errors in the T2S condition compared to the silent condition. At the same time, more over-annotation was recorded. Finally, annotation performance corresponds to participants’ attitudes towards using T2S.

Original language	English
Title of host publication	Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
Place of Publication	Ghent, Belgium
Publisher	European Association for Machine Translation
Pages	251-259
ISBN (Electronic)	9789464597622
Publication status	Published - Jun 2022
Event	The 23rd Annual Conference of the European Association for Machine Translation - Ghent, Belgium Duration: 1 Jun 2022 → 3 Jun 2022 Conference number: 23 https://eamt2022.com/

Conference

Conference	The 23rd Annual Conference of the European Association for Machine Translation
Abbreviated title	EAMT
Country/Territory	Belgium
City	Ghent
Period	1/06/22 → 3/06/22
Internet address	https://eamt2022.com/

Austrian Fields of Science 2012

602051 Translation studies

Access to Document

https://aclanthology.org/2022.eamt-1.28/Licence: CC BY-ND 3.0

Cite this

@inproceedings{9574b7e71b544339942041879049fdad,

title = "Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology",

abstract = "As post-editing of machine translation (PEMT) is becoming one of the most dominant services offered by the language services industry (LSI), efforts are being made to support provision of this service with additional technology. We present text-to-speech (T2S) as a potential attention-raising technology for post-editors. Our study was conducted with university students and included both PEMT and error annotation of a creative text with and without T2S. Focusing on the error annotation data, our analysis finds that participants under-annotated fewer MT errors in the T2S condition compared to the silent condition. At the same time, more over-annotation was recorded. Finally, annotation performance corresponds to participants{\textquoteright} attitudes towards using T2S.",

author = "Justus Brockmann and Wiesinger, \{Claudia Karin\} and Ciobanu, \{Dragos Ioan\}",

year = "2022",

month = jun,

language = "English",

pages = "251--259",

booktitle = "Proceedings of the 23rd Annual Conference of the European Association for Machine Translation",

publisher = "European Association for Machine Translation",

note = "The 23rd Annual Conference of the European Association for Machine Translation, EAMT ; Conference date: 01-06-2022 Through 03-06-2022",

url = "https://eamt2022.com/",

}

Brockmann, J, Wiesinger, CK & Ciobanu, DI 2022, Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology. in Proceedings of the 23rd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Ghent, Belgium, pp. 251-259, The 23rd Annual Conference of the European Association for Machine Translation, Ghent, Belgium, 1/06/22. <https://aclanthology.org/2022.eamt-1.28/>

Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology. / Brockmann, Justus; Wiesinger, Claudia Karin ; Ciobanu, Dragos Ioan.
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation. Ghent, Belgium: European Association for Machine Translation, 2022. p. 251-259.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

TY - GEN

T1 - Error Annotation in Post-Editing Machine Translation

T2 - The 23rd Annual Conference of the European Association for Machine Translation

AU - Brockmann, Justus

AU - Wiesinger, Claudia Karin

AU - Ciobanu, Dragos Ioan

N1 - Conference code: 23

PY - 2022/6

Y1 - 2022/6

N2 - As post-editing of machine translation (PEMT) is becoming one of the most dominant services offered by the language services industry (LSI), efforts are being made to support provision of this service with additional technology. We present text-to-speech (T2S) as a potential attention-raising technology for post-editors. Our study was conducted with university students and included both PEMT and error annotation of a creative text with and without T2S. Focusing on the error annotation data, our analysis finds that participants under-annotated fewer MT errors in the T2S condition compared to the silent condition. At the same time, more over-annotation was recorded. Finally, annotation performance corresponds to participants’ attitudes towards using T2S.

AB - As post-editing of machine translation (PEMT) is becoming one of the most dominant services offered by the language services industry (LSI), efforts are being made to support provision of this service with additional technology. We present text-to-speech (T2S) as a potential attention-raising technology for post-editors. Our study was conducted with university students and included both PEMT and error annotation of a creative text with and without T2S. Focusing on the error annotation data, our analysis finds that participants under-annotated fewer MT errors in the T2S condition compared to the silent condition. At the same time, more over-annotation was recorded. Finally, annotation performance corresponds to participants’ attitudes towards using T2S.

M3 - Contribution to proceedings

SP - 251

EP - 259

BT - Proceedings of the 23rd Annual Conference of the European Association for Machine Translation

PB - European Association for Machine Translation

CY - Ghent, Belgium

Y2 - 1 June 2022 through 3 June 2022

ER -

Error Annotation in Post-Editing Machine Translation: Investigating the Impact of Text-to-Speech Technology

Abstract

Conference

Austrian Fields of Science 2012

Access to Document

Fingerprint

Cite this