Predictive translation memory: a mixed-initiative system for human language translation

The standard approach to computer-aided language translation is post-editing: a machine generates a single translation that a human translator corrects. Recent studies have shown this simple technique to be surprisingly effective, yet it underutilizes the complementary strengths of precision-oriented humans and recall-oriented machines. We present Predictive Translation Memory, an interactive, mixed-initiative system for human language translation. Translators build translations incrementally by considering machine suggestions that update according to the user's current partial translation. In a large-scale study, we find that professional translators are slightly slower in the interactive mode yet produce slightly higher quality translations despite significant prior experience with the baseline post-editing condition. Our analysis identifies significant predictors of time and quality, and also characterizes interactive aid usage. Subjects entered over 99% of characters via interactive aids, a significantly higher fraction than that shown in previous work.

[1]  Jonathan Slocum,et al.  A Survey of Machine Translation: Its History, Current Status and Future Prospects , 1985, CL.

[2]  George F. Foster,et al.  TransType: text prediction for translators , 2002 .

[3]  Shiu-Chang Loh,et al.  AN INTERACTIVE ON-LINE MACHINE TRANSLATION SYSTEM (CHINESE INTO ENGLISH) , 1979 .

[4]  D. Barr,et al.  Random effects structure for confirmatory hypothesis testing: Keep it maximal. , 2013, Journal of memory and language.

[5]  Philip Resnik,et al.  Evaluating Translational Correspondence using Annotation Projection , 2002, ACL.

[6]  Christopher Culy,et al.  The limits of n-gram translation evaluation metrics , 2003, MTSUMMIT.

[7]  Elliott Macklovitch,et al.  The contribution of end-users to the TransType2 project , 2004, AMTA.

[8]  Philipp Koehn,et al.  Scalable Modified Kneser-Ney Language Model Estimation , 2013, ACL.

[9]  Toru Ishida,et al.  Designing Protocols for Collaborative Translation , 2009, PRIMA.

[10]  Philip Koehn,et al.  Statistical Machine Translation , 2010, EAMT.

[11]  Benjamin B. Bederson,et al.  Translation by iterative collaboration between monolingual users , 2010, HCOMP '10.

[12]  Ben Taskar,et al.  Alignment by Agreement , 2006, NAACL.

[13]  Pete Whitelock,et al.  Strategies for Interactive Machine Translation: the experience and implications of the UMIST Japanese project , 1986, COLING.

[14]  Elliott Macklovitch.  TransType2 : The Last Word , 2006, LREC.

[15]  Benjamin B. Bederson,et al.  Deploying monotrans widgets in the wild , 2012, CHI.

[16]  Guy Lapalme,et al.  Tracing Translations in the Making , 2005, MTSUMMIT.

[17]  Philipp Koehn,et al.  Findings of the 2013 Workshop on Statistical Machine Translation , 2013, WMT@ACL.

[18]  Christopher D. Manning,et al.  Phrasal: A Toolkit for New Directions in Statistical Machine Translation , 2014, WMT@ACL.

[19]  Philipp Koehn,et al.  Re-evaluating the Role of Bleu in Machine Translation Research , 2006, EACL.

[20]  Christopher D. Manning,et al.  Fast and Adaptive Online Training of Feature-Rich Translation Models , 2013, ACL.

[21]  Hermann Ney,et al.  Statistical Approaches to Computer-Assisted Translation , 2009, CL.

[22]  George F. Foster,et al.  User-Friendly Text Prediction For Translators , 2002, EMNLP.

[23]  Kenneth Ward Church,et al.  Good applications for crummy machine translation , 1993, Machine Translation.

[24]  Guy Lapalme,et al.  TransType2 - An Innovative Computer-Assisted Translation System , 2004, ACL.

[25]  Germán Sanchis-Trilles,et al.  User Evaluation of Advanced Interaction Features for a Computer-Assisted Translation Workbench , 2013, MTSUMMIT.

[26]  Philippe Langlais,et al.  Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity , 2002, Machine Translation.

[27]  M. Carl.  A computational framework for a cognitive model of human translation processes , 2010, TC.

[28]  Jaime R. Carbonell,et al.  AI in CAI : An artificial intelligence approach to computer-assisted instruction , 1970 .

[29]  Jeffrey Heer,et al.  The efficacy of human post-editing for language translation , 2013, CHI.

[30]  Daniel Jurafsky,et al.  The Best Lexical Metric for Phrase-Based Statistical MT System Optimization , 2010, NAACL.

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

[32]  Francisco Casacuberta,et al.  Advanced computer aided translation with a web-based workbench , 2013, MTSUMMIT.

[33]  Yehoshua Bar-Hillel,et al.  The Present Status of Automatic Translation of Languages , 1960, Adv. Comput..

[34]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[35]  Eric Horvitz,et al.  Principles of mixed-initiative user interfaces , 1999, CHI '99.

[36]  Francisco Casacuberta,et al.  User Evaluation of Interactive Machine Translation Systems , 2012, EAMT.

[37]  Philipp Koehn,et al.  A Web-Based Interactive Computer Aided Translation Tool , 2009, ACL.

[38]  Toru Ishida,et al.  Collaborative translation by monolinguals with machine translators , 2009, IUI.

[39]  Martin Kay,et al.  The MIND Translation System: A Study in Man-Machine Collaboration. , 1972 .

[40]  Pierre Isabelle,et al.  Target-Text Mediated Interactive Machine Translation , 2004, Machine Translation.

[41]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[42]  MARTIN KAY.  The Proper Place of Men and Machines in Language Translation , 2004, Machine Translation.

[43]  Chin-Yew Lin,et al.  ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation , 2004, COLING.