Paper: Improved Discriminative Bilingual Word Alignment

ACL ID P06-1065
Title Improved Discriminative Bilingual Word Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

For many years, statistical machine trans- lation relied on generative models to pro- vide bilingual word alignments. In 2005, several independent efforts showed that discriminative models could be used to enhance or replace the standard genera- tive approach. Building on this work, we demonstrate substantial improvement in word-alignment accuracy, partly though improved training methods, but predomi- nantly through selection of more and bet- ter features. Our best model produces the lowest alignment error rate yet reported on Canadian Hansards bilingual data.