Non-Projective Parsing for Statistical Machine Translation

• Main Authors: Carreras Perez, Xavier (Contributor), Collins, Michael (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Association for Computing Machinery, 2010-10-15T14:58:44Z.
• Subjects: Article
• Online Access: Get fulltext

We describe a novel approach for syntax-based 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 source-language string. Experiments on translation from German to English show improvements over phrase-based systems, both in terms of BLEU scores and in human evaluations.
United States. Defense Advanced Research Projects Agency (GALE program, Contract No. HR0011-06-C-0022)