Non-Projective Parsing for Statistical Machine Translation
Name
Collins_Nonprojective parsing.pdf
Size
119.55 KB
Format
Adobe PDF
Checksum (MD5)
59c9ff50b54118ea0de5820838c65246
Author(s)
Carreras Perez, Xavier
Collins, Michael
Date Issued
2009
Journal
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing
Publisher
Association for Computing Machinery
Citation
Carreras, Xavier, and Michael Collins. “Non-projective parsing for statistical machine translation.” Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1. Singapore: Association for Computational Linguistics, 2009. 200-209.
Version
Author's final manuscript
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Attribution-Noncommercial-Share Alike 3.0 Unported
Persistent DSpace Link
