Fast and Robust Neural Network Joint Models for Statistical Machine Translation
Jacob Devlina b, Rabih M. Zbiba b, Zhongqiang Huanga b, Thomas Lamara b, Richard M. Schwartza b, John I. Makhoula b
- aRaytheon BBN Technologies , 10 Moulton St , Cambridge , MA 02138 , USA
- bBBN Technologies
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Recent work has shown success in using neural network language models (NNLMs) as features in MT systems. Here, we present a novel formulation for a neural network joint model (NNJM), which augments the NNLM with a source context window. Our model is purely lexicalized and can be integrated into any MT decoder. We also present several variations of the NNJM which provide significant additive improvements.
TL;DRA novel formulation for a neural network joint model (NNJM), which augments the NNLM with a source context window, which is purely lexicalized and can be integrated into any MT decoder. (Semantic Scholar)