This study compares consistency in target texts produced using translation memory (TM) with that of target texts produced using statistical machine translation (SMT), where the SMT engine is trained on the same texts as are reused in the TM workflow. These comparisons focus specifically on noun and verb inconsistencies, as such inconsistencies appear to be highly prevalent in TM data. The study substitutes inconsistent TM target text nouns and verbs for consistent nouns and verbs from the SMT output to test whether this results in improvements in overall TM consistency and whether an SMT engine trained on the 'laundered' TM data performs better than the baseline engine. Improvements were observed in both TM consistency and SMT performance, a finding that indicates the potential of this approach for improving TM/MT integration.
:C$\backslash$:/Users/Eva/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Moorkens et al. - 2014 - A virtuous circle laundering translation memory data using statistical machine translation.pdf:pdf
%0 Journal Article
%1 moorkens2014virtuous
%A Moorkens, Joss
%A Doherty, Stephen
%A Kenny, Dorothy
%A O'Brien, Sharon
%D 2014
%J Perspectives: Studies in Translatology
%K memorias_de_traducción tecnologías_de_la_traducción traducción_automática
%N 3
%P 291--303
%R 10.1080/0907676X.2013.811275
%T A virtuous circle: laundering translation memory data using statistical machine translation
%U http://www.researchgate.net/publication/257224982\_A\_Virtuous\_Circle\_Laundering\_Translation\_Memory\_Data\_using\_Statistical\_Machine\_Translation
%V 22
%X This study compares consistency in target texts produced using translation memory (TM) with that of target texts produced using statistical machine translation (SMT), where the SMT engine is trained on the same texts as are reused in the TM workflow. These comparisons focus specifically on noun and verb inconsistencies, as such inconsistencies appear to be highly prevalent in TM data. The study substitutes inconsistent TM target text nouns and verbs for consistent nouns and verbs from the SMT output to test whether this results in improvements in overall TM consistency and whether an SMT engine trained on the 'laundered' TM data performs better than the baseline engine. Improvements were observed in both TM consistency and SMT performance, a finding that indicates the potential of this approach for improving TM/MT integration.
%@ http://dx.doi.org/10.1080/0907676X.2013.811275
@article{moorkens2014virtuous,
abstract = {This study compares consistency in target texts produced using translation memory (TM) with that of target texts produced using statistical machine translation (SMT), where the SMT engine is trained on the same texts as are reused in the TM workflow. These comparisons focus specifically on noun and verb inconsistencies, as such inconsistencies appear to be highly prevalent in TM data. The study substitutes inconsistent TM target text nouns and verbs for consistent nouns and verbs from the SMT output to test whether this results in improvements in overall TM consistency and whether an SMT engine trained on the 'laundered' TM data performs better than the baseline engine. Improvements were observed in both TM consistency and SMT performance, a finding that indicates the potential of this approach for improving TM/MT integration.},
added-at = {2015-12-09T21:07:47.000+0100},
author = {Moorkens, Joss and Doherty, Stephen and Kenny, Dorothy and O'Brien, Sharon},
biburl = {https://www.bibsonomy.org/bibtex/2b26c7f94813f9b2f7e771d65c35159bf/evalopezsainz},
doi = {10.1080/0907676X.2013.811275},
file = {:C$\backslash$:/Users/Eva/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Moorkens et al. - 2014 - A virtuous circle laundering translation memory data using statistical machine translation.pdf:pdf},
interhash = {beb9cfc2f382d3203fada920974c6da7},
intrahash = {b26c7f94813f9b2f7e771d65c35159bf},
isbn = {http://dx.doi.org/10.1080/0907676X.2013.811275},
journal = {Perspectives: Studies in Translatology},
keywords = {memorias_de_traducción tecnologías_de_la_traducción traducción_automática},
mendeley-tags = {machine translation,translation memory,translation technology},
month = oct,
number = 3,
pages = {291--303},
timestamp = {2015-12-10T10:02:09.000+0100},
title = {A virtuous circle: laundering translation memory data using statistical machine translation},
url = {http://www.researchgate.net/publication/257224982{\_}A{\_}Virtuous{\_}Circle{\_}Laundering{\_}Translation{\_}Memory{\_}Data{\_}using{\_}Statistical{\_}Machine{\_}Translation},
volume = 22,
year = 2014
}