Comparing Translator Acceptability of TM and SMT Outputs

This paper reports on an initial study that aims to understand whether the acceptability of translation memory (TM) among translators when contrasted with machine translation (MT) unacceptability is based on users’ ability to optimise precision in match suggestions. Seven translators were asked to rate whether 60 English-German translated segments were a usable basis for a good target translation. 30 segments were from a domain-appropriate TM without a quality threshold being set, and 30 segments were translated by a general domain statistical MT system. Participants found the MT output more useful on average, with only TM fuzzy matches of over 90% considered more useful. This result suggests that, were the MT community able to provide an accurate quality threshold to users, they would consider MT to be the more useful technology.

[1]  Philipp Koehn,et al.  A process study of computer-aided translation , 2009, Machine Translation.

[2]  Andréia Guerini,et al.  Unity in diversity? Current trends in translation studies , 1999 .

[3]  P. Isabelle,et al.  Phrase-based Machine Translation in a Computer-assisted Translation Environment , 2009, MTSUMMIT.

[4]  Lucia Specia,et al.  Exploiting Objective Annotations for Minimising Translation Post-editing Effort , 2011, EAMT.

[5]  鳥飼 玖美子,et al.  テルアビブ国際ワークショップ報告 Profession, Identity and Status: Translators and Interpreters as an Occupational Group , 2009 .

[6]  Andy Way,et al.  COACH: Designing a new CAT tool with Translator Interaction , 2013, MTSUMMIT.

[7]  Tailor-made quality-controlled translation , 2013, TC.

[8]  Jinhua Du,et al.  An empirical study of segment prioritization for incrementally retrained post-editing-based SMT , 2015, MTSUMMIT.

[9]  Yifan He,et al.  Improving the Post-Editing Experience using Translation Recommendation: A User Study , 2010, AMTA.

[10]  Ignacio Garcia.  Translators on translation memories : a blessing or a curse? , 2006 .

[11]  Joss Moorkens,et al.  Towards intelligent post-editing interfaces , 2014 .

[12]  Joseph P. Turian,et al.  Evaluation of machine translation and its evaluation , 2003, MTSUMMIT.

[13]  Sharon O'Brien,et al.  Correlations of perceived post-editing effort with measurements of actual effort , 2015, Machine Translation.

[14]  Pelagia Maria Lagoudaki.  Expanding the possibilities of translation memory systems : from the translators wishlist to the developers design , 2009 .

[15]  Ana Guerberof Arenas.  Productivity and Quality in the Post-editing of Outputs from Translation Memories and Machine Translation , 2008 .

[16]  Minna Ruokonen,et al.  Love letters or hate mail? Translators’ technology acceptance in the light of their emotional narratives , 2017 .

[17]  Sharon O'Brien,et al.  Post-Editing Evaluations: Trade-offs between Novice and Professional Participants , 2015, EAMT.

[18]  Dragos Ciobanu,et al.  Traditional and Emerging Use-Cases for Machine Translation , 2013 .

[19]  Marcello Federico,et al.  Coping with the Subjectivity of Human Judgements in MT Quality Estimation , 2013, WMT@ACL.

[20]  Jeffrey Heer,et al.  Human Effort and Machine Learnability in Computer Aided Translation , 2014, EMNLP.

[21]  Giselle de Almeida,et al.  Translating the post-editor: an investigation of post-editing changes and correlations with professional experience across two Romance languages , 2013 .

[22]  David Katan,et al.  Occupation or profession: A survey of the translators' world , 2011 .

[23]  Nello Cristianini,et al.  Estimating the Sentence-Level Quality of Machine Translation Systems , 2009, EAMT.

[24]  Federico Gaspari,et al.  Perception vs. reality: measuring machine translation post-editing productivity , 2014, AMTA.

[25]  Nadira Hofmann.  MT-enhanced fuzzy matching with Transit NXT and STAR Moses , 2015, EAMT.