120 search results - page 21 / 24 » Weighted Alignment Matrices for Statistical Machine Translat... |
COLING
2010
14 years 4 months ago
2010
Hindi and Urdu share a common phonology, morphology and grammar but are written in different scripts. In addition, the vocabularies have also diverged significantly especially in ...
78
Voted
EMNLP
2007
14 years 11 months ago
2007
We describe a discriminatively trained sequence alignment model based on the averaged perceptron. In common with other approaches to sequence modeling using perceptrons, and in co...
70
Voted
COLING
2010
14 years 4 months ago
2010
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
47
Voted
ACL
2006
14 years 11 months ago
2006
Statistical MT has made great progress in the last few years, but current translation models are weak on re-ordering and target language fluency. Syntactic approaches seek to reme...
ACL
2012
13 years 1 days ago
2012
With a few exceptions, discriminative training in statistical machine translation (SMT) has been content with tuning weights for large feature sets on small development data. Evid...