Paper: Minimum Translation Modeling with Recurrent Neural Networks

ACL ID E14-1003
Title Minimum Translation Modeling with Recurrent Neural Networks
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We introduce recurrent neural network- based Minimum Translation Unit (MTU) models which make predictions based on an unbounded history of previous bilin- gual contexts. Traditional back-off n-gram models suffer under the sparse nature of MTUs which makes estimation of high- order sequence models challenging. We tackle the sparsity problem by modeling MTUs both as bags-of-words and as a sequence of individual source and target words. Our best results improve the out- put of a phrase-based statistical machine translation system trained on WMT 2012 French-English data by up to 1.5 BLEU, and we outperform the traditional n-gram based MTU approach by up to 0.8 BLEU.