546 search results - page 17 / 110 » Improved Word-Level System Combination for Machine Translati... |
90
Voted
FINTAL
2006
15 years 4 months ago
2006
This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based st...
111
Voted
ACL
2010
14 years 10 months ago
2010
This paper proposes to use monolingual collocations to improve Statistical Machine Translation (SMT). We make use of the collocation probabilities, which are estimated from monoli...
103
Voted
EMNLP
2009
14 years 10 months ago
2009
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
124
Voted
PRIS
2008
15 years 1 months ago
2008
Abstract. In statistical machine translation, phrase-based translation (PBT) models lead to a significantly better translation quality over single-word-based (SWB) models. PBT mode...
93
Voted
ECAI
2008
Springer
15 years 2 months ago
2008
Springer
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free"