Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases

Matthias Huck, Hieu Hoang, Philipp Koehn

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

Abstract

We present an effective technique to easily augment GHKM-style syntax-based machine translation systems (Galley et al., 2006) with phrase pairs that do not comply with any syntactic well-formedness constraints. Non-syntactic phrase pairs are distinguished from syntactic ones in order to avoid harming effects. We apply our technique in state-of-the-art string-to-tree and tree-to-string setups. For tree-to-string translation, we furthermore investigate novel approaches for translating with source-syntax GHKM rules in association with input tree constraints and input tree features.
Original languageEnglish
Title of host publicationProceedings of the Ninth Workshop on Statistical Machine Translation
Place of PublicationBaltimore, Maryland, USA
PublisherAssociation for Computational Linguistics
Pages486-498
Number of pages13
Publication statusPublished - 1 Jun 2014

Fingerprint

Dive into the research topics of 'Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases'. Together they form a unique fingerprint.

Cite this