Fast and Robust Neural Network Joint Models for Statistical Machine Translation

@inproceedings{Devlin2014FastAR,
  title={Fast and Robust Neural Network Joint Models for Statistical Machine Translation},
  author={Jacob Devlin and Rabih Zbib and Zhongqiang Huang and Thomas Lamar and Richard M. Schwartz and John Makhoul},
  booktitle={ACL},
  year={2014}
}
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. 

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 319 CITATIONS

Self-Normalization Properties of Language Modeling

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Translation Prediction with Source Dependency-Based Context Representation

VIEW 12 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

NRC Russian-English Machine Translation System for WMT 2016

  • WMT
  • 2016
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

The JHU Machine Translation Systems for WMT 2016

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Deep Neural Language Models for Machine Translation

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Encoding Source Language with Convolutional Neural Network for Machine Translation

  • ACL
  • 2015
VIEW 20 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Local Translation Prediction with Global Sentence Representation

  • IJCAI
  • 2015
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Statistical Machine Translation Features with Multitask Tensor Networks

VIEW 26 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!

  • WMT@EMNLP
  • 2015
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 61 Highly Influenced Citations

  • Averaged 39 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 29 REFERENCES