Paper: Probabilistic Inference for Machine Translation

ACL ID D08-1023
Title Probabilistic Inference for Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2008

We advance the state-of-the-art for discrimi- natively trained machine translation systems by presenting novel probabilistic inference and search methods for synchronous gram- mars. By approximating the intractable space of all candidate translations produced by inter- secting an ngram language model with a synchronous grammar, we are able to train and decode models incorporating millions of sparse, heterogeneous features. Further, we demonstrate the power of the discriminative training paradigm by extracting structured syntactic features, and achieving increases in translation performance.