Predicting Post-Editor Profiles from the Translation Process

Karan Singla; David Orrego-Carmona; Ashleigh Rhea Gonzales; Michael Carl; Srinivas  Bangalore

Predicting Post-Editor Profiles from the Translation Process

Karan Singla, David Orrego-Carmona, Ashleigh Rhea Gonzales, Michael Carl, Srinivas Bangalore

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

43 Downloads (Pure)

Abstract

The purpose of the current investigation is to predict post-editor profiles based on user behaviour and demographics using machine learning techniques to gain a better understanding of post-editor styles. Our study extracts process unit features from the CasMaCat LS14 database from the CRITT Translation Process Research Database (TPR-DB). The analysis has two main research goals: We create n-gram models based on user activity and part-of-speech sequences
to automatically cluster post-editors, and we use discriminative classifier models to characterize post-editors based on a diverse range of translation process features. The classification and clustering of participants resulting from our study suggest this type of exploration could be used as a tool to develop new translation tool features or customization possibilities.

Originalsprog	Engelsk
Titel	Proceedings of the Workshop on Interactive and Adaptive Machine Translation
Redaktører	Francisco Casacuberta, Marcello Federico, Philipp Koehn
Antal sider	10
Forlag	Association for Machine Translation in the Americas (AMTA)
Publikationsdato	2014
Sider	51-60
Status	Udgivet - 2014
Begivenhed	The 11th Conference of the Association for Machine Translation in the Americas 2014 - Vancouver, Canada Varighed: 22 okt. 2014 → 26 okt. 2014 Konferencens nummer: 11 http://amta2014.amtaweb.org/

Konference

Konference	The 11th Conference of the Association for Machine Translation in the Americas 2014
Nummer	11
Land/Område	Canada
By	Vancouver
Periode	22/10/2014 → 26/10/2014
Internetadresse	http://amta2014.amtaweb.org/

Adgang til dokumentet

Michael Carl_ AMTA2014Proceedings_2Forlagets udgivne version, 193 KBLicens: CC BY-NC-ND

http://www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proceedings_IAMTWorkshop_final.pdfLicens: Ikke-specificeret

Handle.net

Persistent link

Citationsformater

Singla, K., Orrego-Carmona, D., Gonzales, A. R., Carl, M., & Bangalore, S. (2014). Predicting Post-Editor Profiles from the Translation Process. I F. Casacuberta, M. Federico, & P. Koehn (red.), Proceedings of the Workshop on Interactive and Adaptive Machine Translation (s. 51-60). Association for Machine Translation in the Americas (AMTA). http://www.amtaweb.org/AMTA2014Proceedings/AMTA2014Proceedings_IAMTWorkshop_final.pdf

@inproceedings{8667ac6621e2458684ba77bf33115ead,

title = "Predicting Post-Editor Profiles from the Translation Process",

abstract = "The purpose of the current investigation is to predict post-editor profiles based on user behaviour and demographics using machine learning techniques to gain a better understanding of post-editor styles. Our study extracts process unit features from the CasMaCat LS14 database from the CRITT Translation Process Research Database (TPR-DB). The analysis has two main research goals: We create n-gram models based on user activity and part-of-speech sequencesto automatically cluster post-editors, and we use discriminative classifier models to characterize post-editors based on a diverse range of translation process features. The classification and clustering of participants resulting from our study suggest this type of exploration could be used as a tool to develop new translation tool features or customization possibilities.",

author = "Karan Singla and David Orrego-Carmona and Gonzales, {Ashleigh Rhea} and Michael Carl and Srinivas Bangalore",

year = "2014",

language = "English",

pages = "51--60",

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/",

}

Singla, K, Orrego-Carmona, D, Gonzales, AR, Carl, M & Bangalore, S 2014, Predicting Post-Editor Profiles from the Translation Process. i F Casacuberta, M Federico & P Koehn (red), Proceedings of the Workshop on Interactive and Adaptive Machine Translation. Association for Machine Translation in the Americas (AMTA), s. 51-60, 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>

Predicting Post-Editor Profiles from the Translation Process. / Singla, Karan; Orrego-Carmona, David; Gonzales, Ashleigh Rhea et al.
Proceedings of the Workshop on Interactive and Adaptive Machine Translation. red. / Francisco Casacuberta; Marcello Federico; Philipp Koehn. Association for Machine Translation in the Americas (AMTA), 2014. s. 51-60.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Predicting Post-Editor Profiles from the Translation Process

AU - Singla, Karan

AU - Orrego-Carmona, David

AU - Gonzales, Ashleigh Rhea

AU - Carl, Michael

AU - Bangalore, Srinivas

N1 - Conference code: 11

PY - 2014

Y1 - 2014

N2 - The purpose of the current investigation is to predict post-editor profiles based on user behaviour and demographics using machine learning techniques to gain a better understanding of post-editor styles. Our study extracts process unit features from the CasMaCat LS14 database from the CRITT Translation Process Research Database (TPR-DB). The analysis has two main research goals: We create n-gram models based on user activity and part-of-speech sequencesto automatically cluster post-editors, and we use discriminative classifier models to characterize post-editors based on a diverse range of translation process features. The classification and clustering of participants resulting from our study suggest this type of exploration could be used as a tool to develop new translation tool features or customization possibilities.

AB - The purpose of the current investigation is to predict post-editor profiles based on user behaviour and demographics using machine learning techniques to gain a better understanding of post-editor styles. Our study extracts process unit features from the CasMaCat LS14 database from the CRITT Translation Process Research Database (TPR-DB). The analysis has two main research goals: We create n-gram models based on user activity and part-of-speech sequencesto automatically cluster post-editors, and we use discriminative classifier models to characterize post-editors based on a diverse range of translation process features. The classification and clustering of participants resulting from our study suggest this type of exploration could be used as a tool to develop new translation tool features or customization possibilities.

M3 - Article in proceedings

SP - 51

EP - 60

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 -