16 search results - page 1 / 4 » Exploring the Use of Target-Language Information to Train th... |
TAL
2004
Springer
13 years 10 months ago
2004
Springer
ACL
2008
13 years 6 months ago
2008
A Named Entity Recognizer (NER) generally has worse performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As som...
COLING
2010
12 years 11 months ago
2010
An unsupervised discriminative training procedure is proposed for estimating a language model (LM) for machine translation (MT). An English-to-English synchronous context-free gra...
MT
2007
13 years 4 months ago
2007
Statistical machine translation systems are usually trained on large amounts of bilingual text (used to learn a translation model), and also large amounts of monolingual text in th...
ACL
2008
13 years 6 months ago
2008
We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic information...