Integrating Online and Active Learning in a Computer-Assisted Translation Workbench

Vicent Alabau; Jésus González-Rubio; Daniel  Ortíz-Martínez; Francisco Casacuberta; Mercedes Garcia Martinez; Bartolomé  Mesa-Lao; Dan Cheung  Petersen; Barbara Dragsted; Michael Carl

Integrating Online and Active Learning in a Computer-Assisted Translation Workbench

Vicent Alabau, Jésus González-Rubio, Daniel Ortíz-Martínez , Francisco Casacuberta, Mercedes Garcia Martinez, Bartolomé Mesa-Lao, Dan Cheung Petersen, Barbara Dragsted, Michael Carl

Polytechnic University of Valencia

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

106 Downloads (Pure)

Abstract

This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.

Original language	English
Title of host publication	Proceedings of the Workshop on Interactive and Adaptive Machine Translation
Editors	Francisco Casacuberta, Marcello Federico, Philipp Koehn
Number of pages	8
Publisher	Association for Machine Translation in the Americas (AMTA)
Publication date	2014
Pages	1-8
Publication status	Published - 2014
Event	The 11th Conference of the Association for Machine Translation in the Americas 2014 - Vancouver, Canada Duration: 22 Oct 2014 → 26 Oct 2014 Conference number: 11 http://amta2014.amtaweb.org/

Conference

Conference	The 11th Conference of the Association for Machine Translation in the Americas 2014
Number	11
Country/Territory	Canada
City	Vancouver
Period	22/10/2014 → 26/10/2014
Internet address	http://amta2014.amtaweb.org/

Access to Document

Michael Carl_ AMTA2014Proceedings_1Final published version, 289 KBLicence: CC BY-NC-ND

http://www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proceedings_IAMTWorkshop_final.pdfLicence: Unspecified

Handle.net

Persistent link

Cite this

Alabau, V., González-Rubio, J., Ortíz-Martínez , D., Casacuberta, F., Martinez, M. G., Mesa-Lao, B., Petersen, D. C., Dragsted, B., & Carl, M. (2014). Integrating Online and Active Learning in a Computer-Assisted Translation Workbench. In F. Casacuberta, M. Federico, & P. Koehn (Eds.), Proceedings of the Workshop on Interactive and Adaptive Machine Translation (pp. 1-8). Association for Machine Translation in the Americas (AMTA). http://www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proceedings_IAMTWorkshop_final.pdf

Alabau, Vicent ; González-Rubio, Jésus ; Ortíz-Martínez , Daniel et al. / Integrating Online and Active Learning in a Computer-Assisted Translation Workbench. Proceedings of the Workshop on Interactive and Adaptive Machine Translation. editor / Francisco Casacuberta ; Marcello Federico ; Philipp Koehn. Association for Machine Translation in the Americas (AMTA), 2014. pp. 1-8

@inproceedings{dba361ab9923490bad9f2169824a7362,

title = "Integrating Online and Active Learning in a Computer-Assisted Translation Workbench",

abstract = "This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.",

author = "Vicent Alabau and J{\'e}sus Gonz{\'a}lez-Rubio and Daniel Ort{\'i}z-Mart{\'i}nez and Francisco Casacuberta and Martinez, {Mercedes Garcia} and Bartolom{\'e} Mesa-Lao and Petersen, {Dan Cheung} and Barbara Dragsted and Michael Carl",

year = "2014",

language = "English",

pages = "1--8",

editor = "Francisco Casacuberta and Marcello Federico and Philipp Koehn",

booktitle = "Proceedings of the Workshop on Interactive and Adaptive Machine Translation",

publisher = "Association for Machine Translation in the Americas (AMTA)",

address = "United States",

note = "The 11th Conference of the Association for Machine Translation in the Americas 2014 ; Conference date: 22-10-2014 Through 26-10-2014",

url = "http://amta2014.amtaweb.org/",

}

Alabau, V, González-Rubio, J, Ortíz-Martínez , D, Casacuberta, F, Martinez, MG, Mesa-Lao, B, Petersen, DC, Dragsted, B & Carl, M 2014, Integrating Online and Active Learning in a Computer-Assisted Translation Workbench. in F Casacuberta, M Federico & P Koehn (eds), Proceedings of the Workshop on Interactive and Adaptive Machine Translation. Association for Machine Translation in the Americas (AMTA), pp. 1-8, The 11th Conference of the Association for Machine Translation in the Americas 2014, Vancouver, Canada, 22/10/2014. <http://www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proceedings_IAMTWorkshop_final.pdf>

Integrating Online and Active Learning in a Computer-Assisted Translation Workbench. / Alabau, Vicent; González-Rubio, Jésus; Ortíz-Martínez , Daniel et al.
Proceedings of the Workshop on Interactive and Adaptive Machine Translation. ed. / Francisco Casacuberta; Marcello Federico; Philipp Koehn. Association for Machine Translation in the Americas (AMTA), 2014. p. 1-8.

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

TY - GEN

T1 - Integrating Online and Active Learning in a Computer-Assisted Translation Workbench

AU - Alabau, Vicent

AU - González-Rubio, Jésus

AU - Ortíz-Martínez , Daniel

AU - Casacuberta, Francisco

AU - Martinez, Mercedes Garcia

AU - Mesa-Lao, Bartolomé

AU - Petersen, Dan Cheung

AU - Dragsted, Barbara

AU - Carl, Michael

N1 - Conference code: 11

PY - 2014

Y1 - 2014

N2 - This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.

AB - This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.

M3 - Article in proceedings

SP - 1

EP - 8

BT - Proceedings of the Workshop on Interactive and Adaptive Machine Translation

A2 - Casacuberta, Francisco

A2 - Federico, Marcello

A2 - Koehn, Philipp

PB - Association for Machine Translation in the Americas (AMTA)

T2 - The 11th Conference of the Association for Machine Translation in the Americas 2014

Y2 - 22 October 2014 through 26 October 2014

ER -

Alabau V, González-Rubio J, Ortíz-Martínez D, Casacuberta F, Martinez MG, Mesa-Lao B et al. Integrating Online and Active Learning in a Computer-Assisted Translation Workbench. In Casacuberta F, Federico M, Koehn P, editors, Proceedings of the Workshop on Interactive and Adaptive Machine Translation. Association for Machine Translation in the Americas (AMTA). 2014. p. 1-8