164 search results - page 6 / 33 » Improved Word Alignment with Statistics and Linguistic Heuri... |
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 ...
84
Voted
AMTA
2004
Springer
15 years 3 months ago
2004
Springer
In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentencealigned training corpora. Others employ dic...
96
Voted
IJCNLP
2005
Springer
15 years 3 months ago
2005
Springer
Abstract. This paper proposes an approach to improve statistical word alignment with ensemble methods. Two ensemble methods are investigated: bagging and cross-validation committee...
86
Voted
ACL
2009
14 years 7 months ago
2009
Recently confusion network decoding shows the best performance in combining outputs from multiple machine translation (MT) systems. However, overcoming different word orders prese...
FINTAL
2006
15 years 1 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...