Paper: Consistent Translation using Discriminative Learning - A Translation Memory-inspired Approach

ACL ID P11-1124
Title Consistent Translation using Discriminative Learning - A Translation Memory-inspired Approach
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

We present a discriminative learning method to improve the consistency of translations in phrase-based Statistical Machine Translation (SMT) systems. Our method is inspired by Translation Memory (TM) systems which are widely used by human translators in industrial settings. We constrain the translation of an in- put sentence using the most similar ‘transla- tion example’ retrieved from the TM. Differ- ently from previous research which used sim- ple fuzzy match thresholds, these constraints are imposed using discriminative learning to optimise the translation performance. We ob- serve that using this method can benefit the SMT system by not only producing consis- tent translations, but also improved translation outputs. We report a 0.9 point improvement in terms of BLEU score on Englis...