A ranking method for example based machine translation results by learning from user feedback

Abstract

Example-Based Machine Translation (EBMT) is a corpus based approach to Machine Translation (MT), that utilizes the translation by analogy concept. In our EBMT system, translation templates are extracted automatically from bilingual aligned corpora by substituting the similarities and differences in pairs of translation examples with variables. In the earlier versions of the discussed system, the translation results were solely ranked using confidence factors of the translation templates. In this study, we introduce an improved ranking mechanism that dynamically learns from user feedback. When a user, such as a professional human translator, submits his evaluation of the generated translation results, the system learns "context-dependent co-occurrence rules" from this feedback. The newly learned rules are later consulted, while ranking the results of the subsequent translations. Through successive translation-evaluation cycles, we expect that the output of the ranking mechanism complies better with user expectations, listing the more preferred results in higher ranks. We also present the evaluation of our ranking method which uses the precision values at top results and the BLEU metric. © 2010 Springer Science+Business Media, LLC

An Incremental Technique of Improving Translation

“…The proposed work uses the same idea of enhanced confidence with the help of an automatic tool, BLEU, for evaluation of translated output of one pass to be used as input for translation of next pass. Daybelge and Cicekli [17] have used a similar approach of using BLEU score as a measure of incremental learning and reported improvement in the translation quality using example based machine translation. Quality of translation does not depend only on the syntax and morphology but also on the sense of the source word [18; 19].…”