A Study of State-of-the-Art Neural Machine Translation Approaches

Authors

  • Mr. Satish Kumar  Department of Information Technology, Baba Ghulam Shah Badshah University, Rajouri-185131, (J&K), India
  • Dr. Mohammed Asger  Department of Computer Sciences, Baba Ghulam Shah Badshah University, Rajouri-185131, (J&K), India

Keywords:

Neural Network, Neural Machine Translation, Back Propagation Training, Refinements, encoder-decoder approach, attention-based model Feedforword approach

Abstract

Neural Machine Translation (NMT) is a recent advance proposal technique in machine translation. Neural Machine Translation surpassed the results of Statistical Machine Translation. This report discusses some significant works on the recent advances in neural machine translation. The aim of NMT is to build a single neural network that generates maximum translation performance. This report present the overview of neural network, neural language model which include Recurrent Neural Models (RNN) and Neural Machine Translation models which include encoder-decoder approach, attention-based neural machine translation.

References

  1. K. Cho, B. Merrienboer, D. Bahdanau and Y. Bengio. On the Properties of Neural Machine Translation: Encoder–Decoder Approaches.
  2. A. Graves, N. Jaitly and A. Mohamed. Hybrid Speech Recognition with Deep Bidirectional LSTM , 2013.
  3. D. Bahdanau, K. Cho and Y. Bengio. Neural Machine Translation by Jointly Learning to Align and Translate. ICLR, 2015.
  4. K. Cho. Introduction to Neural Machine Translation with GPUs .
  5. O. Vinyals, A. Toshev, S. Bengio and D. Erhan. Show and Tell: A Neural Image Caption Generator. 20 Apr 2015.
  6. K. Cho, A. Courville and Y. Bengio. Describing Multimedia Content using Attention-based Encoder--Decoder Networks. IEEE Transactions on Multimedia, 2015.
  7. R.Sennrich, B. Haddow, A. Birch. Neural Machine Translation of Rare Words with Subword Units. ACL, 2016.
  8. M. Schuster and K. Nakajima. Japanese and Korean voice search. ICASSP, 2012.
  9. Y. Wu, M. Schuster, Z. Chen, Q. Le, M. Norouzi and the Google Brain team. Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. 8 Oct 2016
  10.  A.Graves and N. Jaitly. Towards End-To-End Speech Recognition with Recurrent Neural Networks. ICML, 2014.
  11.  J. Gu, G. Neubig, K. Cho and V. Li. Learning to Translate in Real-time with Neural Machine Translation. 10 Jan 2017
  12.  Karpathy. The Unreasonable Effectiveness of Recurrent Neural Networks .
  13.  Neural Machine Translation (ACL 2016 Tutorial)
  14.  Y. Bengio, A. Courville and P.l Vincent. Representation Learning: A Review and New Perspectives. 23 Apr 2014

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-04-25

Issue

Volume 4, Issue 1, March-April-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Mr. Satish Kumar, Dr. Mohammed Asger, " A Study of State-of-the-Art Neural Machine Translation Approaches, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 4, Issue 1, pp.135-139, March-April-2018.