While Inversion Transduction Grammar (ITG) has regained more and more attention in recent years, it still suffers from the major obstacle of speed. We propose a discriminative ITG...
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...
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
Aria Haghighi, John Blitzer, John DeNero, Dan Klei...
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...
Syntactic machine translation systems extract rules from bilingual, word-aligned, syntactically parsed text, but current systems for parsing and word alignment are at best cascade...