Machine Translation Using Deep Learning : A Survey
Keywords:
Machine Translation, Neural Networks, Neural Machine Translation, Deep LearningAbstract
Machine Translation using Deep Learning (Neural Machine Translation) is a newly proposed approach to machine translation. The term Machine Translation is used in the sense of translation of one language to another, with no human improvement. It can also be referred to as automated translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. This survey reveals the information about Deep Neural Network (DNN) and concept of deep learning in field of natural language processing i.e. machine translation. It is better to use Recurrent Neural Network(RNN) in Machine Translation. This paper studies various techniques used to train RNN for various language corpuses. RNN structure is very complicated and to train a large corpus is also a time-consuming task. Hence, a powerful hardware support (Graphics Processing Unit) is required. GPU improves the system performance by decreasing training time period.
References
- Jiajun Zhang and Chengqing Zong,"Deep neural networks in machine translation : An overview", in IEEE intelligent system, 2015.
- Kyunghyun Cho, Aaron Courville, and Yoshua Bengio, "Describing multimedia content using attention based Encoder-Decoder network", IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 17, NO. 11, NOVEMBER 2015.
- Sanjanaashree P, and Anand Kumar M, "Joint Layer based Deep Learning Framework for Bilingual Machine Transliteration", IEEE, 2015.
- Zhen Yang, Wei Chen, Feng Wang, Bo Xu, "Multi-Sense Based Neural Machine Translation",in IEEE, 2017.
- XIAO-XUE WANG, CONG-HUI ZHU, SHENG LI, TIE-JUN ZHAO, DE-QUAN ZHENG, "Neural Machine Translation Research Based On The Semantic Vector Of The Tri-lingual Parallel Corpus", in IEEE, 2016.
- Feng Wang, Wei Chen[1] ,Zhen Yang, Xiaowei Zhang, Shuang xu, Bo Xu, "A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation", in IEEE, 2017.
- Andi Hermanto, Teguh Bharata Adji, Noor Akhmad Setiawan, "Recurrent Neural Network Language Model for English-Indonesian Machine Translation: Experimental Study", in IEEE, 2015.
- Biao Zhang, Deyi Xiong, Jinsong Su, and Hong Duan, "A Context-Aware Recurrent Encoder for Neural Machine Translation", IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 12, DECEMBER 2017.
- Deep Learning – Wikipedia, https://en.wikipedia.org/wiki/Deep_learning .
- Xiao Sun, Xiaoqi Peng, Fuji Ren, Yun Xue, "Human-Machine Conversation Based on Hybrid Neural Network", in IEEE, 2017.
- Sandeep Saini, Vineet Sahula, "A Survey of Machine Translation Techniques and Systems for Indian Languages", in IEEE, 2015.
- Eric Greenstein, Daniel Penner, "Japanese-to-English Machine Translation Using Recurrent Neural Networks", available at https://github.com/lisagroundhog/GroundHog.
- Bing Zhao, Yik-Cheung Tam, "BILINGUAL RECURREN T NEURAL NETWORKS FOR IMPROVED STATISTICAL MACHINE TRANSLATION", in IEEE, 2014.
- Preeti Dubey, "Need for Hindi-Dogri Machine Translation System", in IEEE, 2014.
- Heeyoul Choi, Kyunghyun Cho, Yoshua Bengio, "Context-dependent word representation for neural machine translation", in Elsevier, 2017.
- Todd Law, Hidenori Itoh, Hirohisa Seki,"A neural network assisted Japanese-English Machine translation system", International Joint Conference on Neural Networks, 1993.
- KyungHyun Cho, Yoshua Bengio,"NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE ", in ICLR, 2015.
- Neural Machine Translation Tutorial- https://sites.google.com/site/acl16nmt/home
Downloads
Published
Issue
Section
License
Copyright (c) IJSRSET
This work is licensed under a Creative Commons Attribution 4.0 International License.