Non-projective parsing for statistical machine translation
Document typeConference report
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
We describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly flexible reordering operations during parsing, in combination with a discriminative model that can condition on rich features of the sourcelanguage string. Experiments on translation from German to English show improvements over phrase-based systems, both in terms of BLEU scores and in human evaluations.
CitationCarreras, X.; Collins, M. Non-projective parsing for statistical machine translation. A: Conference on Empirical Methods in Natural Language Processing. "Conference on Empirical Methods in Natural Language Processing 2009". Singapur: 2009, p. 200-209.