126 search results - page 3 / 26 » Improving Statistical Natural Language Translation with Cate... |
CICLING
2009
Springer
14 years 9 months ago
2009
Springer
We use existing tools to automatically build two parallel treebanks from existing parallel corpora. We then show that combining the data extracted from both the treebanks and the ...
EMNLP
2010
13 years 6 months ago
2010
We examine effects that empty categories have on machine translation. Empty categories are elements in parse trees that lack corresponding overt surface forms (words) such as drop...
FINTAL
2006
14 years 6 days 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...
EMNLP
2009
13 years 6 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...
EMNLP
2010
13 years 6 months ago
2010
In this article, an original view on how to improve phrase translation estimates is proposed. This proposal is grounded on two main ideas: first, that appropriate examples of a gi...