Paper: Soft Syntactic Constraints For Word Alignment Through Discriminative Training

ACL ID P06-2014
Title Soft Syntactic Constraints For Word Alignment Through Discriminative Training
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

Word alignment methods can gain valu- able guidance by ensuring that their align- ments maintain cohesion with respect to the phrases specified by a monolingual de- pendency tree. However, this hard con- straint can also rule out correct alignments, and its utility decreases as alignment mod- els become more complex. We use a pub- licly available structured output SVM to create a max-margin syntactic aligner with a soft cohesion constraint. The resulting aligner is the first, to our knowledge, to use a discriminative learning method to train an ITG bitext parser.