51 search results - page 1 / 11 » Better Word Alignments with Supervised ITG Models |
ACL
2009
13 years 2 months ago
2009
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
COLING
2010
12 years 11 months ago
2010
While ITG has many desirable properties for word alignment, it still suffers from the limitation of one-to-one matching. While existing approaches relax this limitation using phra...
ACL
2006
13 years 6 months ago
2006
Word alignment methods can gain valuable guidance by ensuring that their alignments maintain cohesion with respect to the phrases specified by a monolingual dependency tree. Howev...
NAACL
2010
13 years 2 months ago
2010
Syntactic machine translation systems currently use word alignments to infer syntactic correspondences between the source and target languages. Instead, we propose an unsupervised...
EMNLP
2010
13 years 2 months ago
2010
Word alignment plays a central role in statistical MT (SMT) since almost all SMT systems extract translation rules from word aligned parallel training data. While most SMT systems...