Benjamin Wellington


2006

pdf bib
Empirical Lower Bounds on the Complexity of Translational Equivalence
Benjamin Wellington | Sonjia Waxmonsky | I. Dan Melamed
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
Scalable Purely-Discriminative Training for Word and Tree Transducers
Benjamin Wellington | Joseph Turian | Chris Pike | Dan Melamed
Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers

Discriminative training methods have recently led to significant advances in the state of the art of machine translation (MT). Another promising trend is the incorporation of syntactic information into MT systems. Combining these trends is difficult for reasons of system complexity and computational complexity. The present study makes progress towards a syntax-aware MT system whose every component is trained discriminatively. Our main innovation is an approach to discriminative learning that is computationally efficient enough for large statistical MT systems, yet whose accuracy on translation sub-tasks is near the state of the art. Our source code is downloadable from http://nlp.cs.nyu.edu/GenPar/.

2004

pdf bib
Generalized Multitext Grammars
I. Dan Melamed | Giorgio Satta | Benjamin Wellington
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)