18 search results - page 1 / 4 » Learning Tractable Word Alignment Models with Complex Constr... |
COLING
2010
13 years 11 months ago
2010
ACL
2006
14 years 17 days 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...
ACL
2011
13 years 2 months ago
2011
We cast the word alignment problem as maximizing a submodular function under matroid constraints. Our framework is able to express complex interactions between alignment component...
NIPS
2007
14 years 17 days ago
2007
The expectation maximization (EM) algorithm is a widely used maximum likelihood estimation procedure for statistical models when the values of some of the variables in the model a...
ACL
2009
13 years 9 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...