Sciweavers

Share
EMNLP
2008

Online Large-Margin Training of Syntactic and Structural Translation Features

10 years 4 months ago
Online Large-Margin Training of Syntactic and Structural Translation Features
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimize. Building on the work of Watanabe et al., we explore the use of the MIRA algorithm of Crammer et al. as an alternative to MERT. We first show that by parallel processing and exploiting more of the parse forest, we can obtain results using MIRA that match or surpass MERT in terms of both translation quality and computational cost. We then test the method on two classes of features that address deficiencies in the Hiero hierarchical phrasebased model: first, we simultaneously train a large number of Marton and Resnik's soft syntactic constraints, and, second, we introduce a novel structural distortion model. In both cases we obtain significant improvements in translation performance. Optimizing them in combination, for a total of 56 feature weights, we improve performance by 2.6 BLEU on a subset of the ...
David Chiang, Yuval Marton, Philip Resnik
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where EMNLP
Authors David Chiang, Yuval Marton, Philip Resnik
Comments (0)
books