Publications

Publication details [#4588]

Publication type
Article in jnl/bk
Publication language
English

Abstract

One of the problems facing translation systems that automatically extract transfer mappings (rules or examples) from bilingual corpora is the trade-off between contextual specificity and general applicability of the mappings, which typically results in conflicting mappings without distinguishing context. The author presents a machine-learning approach to choosing between such mappings, using classifiers that, in effect, selectively expand the context for these mappings using features available in a linguistic representation of the source language input. The author shows that using these classifiers in the machine translation system significantly improves the quality of the translated output. Additionally, the set of distinguishing features selected by the classifiers provides insight into the relative importance of the various linguistic features in choosing the correct contextual translation.
Source : Bitra