Improving the Precision of Example-Based Machine Translation by Learning from User Feedback


Turhan Osman Daybelge
Computer Engineering Department
Bilkent University

Example-Based Machine Translation (EBMT) is a Machine Learning approach that utilizes the translation by analogy concept. In EBMT, translation templates are extracted automatically from bilingual aligned corpora, by substituting the similarities and differences in pairs of translation examples, with variables. As this process is done on the lexical-level forms of the translation examples, and words in natural language texts are often morphologically ambiguous, a need for morphological disambiguation arises. Therefore we prepared a rule-based morphological disambiguator for Turkish. In previous versions of our 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, evaluates the translation results generated, the system learns Context-Dependent Co-occurrence Rules from this feedback. The learned rules are later consulted, while ranking the results of the following translations. Through successive translation-evaluation cycles, we aim that the output of the ranking mechanism complies better with the user expectations, in terms of listing the more preferred results in higher ranks. We evaluate our ranking method by using the precision value at top 1, 3 and 5 results and the BLEU metric.


DATE: 31 August, 2007, Friday@ 10:00