Agreement Constraints for Statistical Machine Translation into German

Philip Williams, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Languages with rich inflectional morphology pose a difficult challenge for statistical machine translation. To address the problem of morphologically inconsistent output, we add unification-based constraints to the target-side of a string-to-tree model. By integrating constraint evaluation into the decoding process, implausible hypotheses can be penalised or filtered out during search. We use a simple heuristic process to extract agreement constraints for German and test our approach on an English-German system trained on WMT data, achieving a small improvement in translation accuracy as measured by BLEU.
Original languageEnglish
Title of host publicationProceedings of the Sixth Workshop on Statistical Machine Translation
Place of PublicationEdinburgh, Scotland
PublisherAssociation for Computational Linguistics
Pages217-226
Number of pages10
Publication statusPublished - 1 Jul 2011

Fingerprint

Dive into the research topics of 'Agreement Constraints for Statistical Machine Translation into German'. Together they form a unique fingerprint.

Cite this