论文信息 - User Evaluation of Interactive Machine Translation Systems

User Evaluation of Interactive Machine Translation Systems

Recent developments in search algorithms and software architecture have enabled multi-user web-based prototypes for Interactive Machine Translation (IMT), a technology that aims to assist, rather than replace, the human translator. Surprisingly, formal human evaluations of IMT systems are highly scarce in the literature. To this regard, we discuss experiences gained while testing IMT systems. We report the lessons learned from two user evaluations. Our results can provide researchers and practitioners with several guidelines towards the design of on-line IMT tools.

Francisco Casacuberta | Daniel Ortiz-Martínez | Vincent Alabau | Luis A. Leiva

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

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

[3] Philipp Koehn,et al. Enabling Monolingual Translators: Post-Editing vs. Options , 2010, NAACL.

[4] Alejandro Héctor Toselli,et al. Evaluating an Interactive-Predictive Paradigm on Handwriting Transcription: A Case Study and Lessons Learned , 2011, 2011 IEEE 35th Annual Computer Software and Applications Conference.

[5] Francisco Casacuberta,et al. Human interaction for high-quality machine translation , 2009, CACM.