A French to English Language Translator Using Recurrent Neural Network with Attention Mechanism

In today’s world there are many people who are facing the problem of language translator for ex: talking to a person who only knows a language which you do not understand or you have some information in a language like French and you only Know English, etc. This type of problem can be overcome by a technology called machine translation. This paper proposed machine translation using the recurrent neural network with attention mechanism, where the recurrent neural network (RNN) are types of neural networks designed for capturing information from sequence and time series data. RNN is useful to learn pattern in a given set of data as the human language is one big complex pattern or a complicated pattern. In machine translation, two recurrent neural networks work together for the transformation of one sequence to the other sequence. An encoder network will change an input sequence in a vector and on the other hand the decoder network will change the vector in a new sequence. To improve the above-stated RNN model we will use the attention mechanism which helps to focus on the specific range of the input sequences.

[1]  Yan Huang,et al.  History attention for source-target alignment in neural machine translation , 2018, 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI).

[2]  Yang Zhang,et al.  Sequence-to-sequence prediction of personal computer software by recurrent neural network , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[3]  Wu Guo,et al.  Recursive annotations for attention-based neural machine translation , 2017, 2017 International Conference on Asian Language Processing (IALP).

[4]  Conghui Zhu,et al.  Neural machine translation research based on the semantic vector of the tri-lingual parallel corpus , 2016, 2016 International Conference on Machine Learning and Cybernetics (ICMLC).

[5]  Kam-Fai Wong,et al.  Recurrent Neural Networks with External Memory for Spoken Language Understanding , 2015, NLPCC.

[6]  Noor Akhmad Setiawan,et al.  Recurrent neural network language model for English-Indonesian Machine Translation: Experimental study , 2015, 2015 International Conference on Science in Information Technology (ICSITech).

[7]  Alexander F. Gelbukh.  Natural Language Processing , 2005, HIS.

[8]  Kazunori Matsumoto,et al.  Sequence-to-Sequence Model with Attention for Time Series Classification , 2016, 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW).

[9]  Lemao Liu,et al.  A Neural Approach to Source Dependence Based Context Model for Statistical Machine Translation , 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[10]  Liang Lu,et al.  On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Rabab Kreidieh Ward,et al.  Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[12]  Zhengchen Zhang,et al.  A light-weight method of building an LSTM-RNN-based bilingual tts system , 2017, 2017 International Conference on Asian Language Processing (IALP).

[13]  A. R. Babhulgaonkar,et al.  Statistical machine translation , 2017, 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM).

[14]  Dipti Misra Sharma,et al.  Building an Effective MT System for English-Hindi Using RNN's , 2017 .

[15]  Peter P. Toma,et al.  SYSTRAN Machine Translation System. , 1970 .

[16]  V. K. Bhadran,et al.  Preprocessors in NLP applications: In the context of English to Malayalam Machine Translation , 2012, 2012 Annual IEEE India Conference (INDICON).

[17]  Sandeep Saini,et al.  A Survey of Machine Translation Techniques and Systems for Indian Languages , 2015, 2015 IEEE International Conference on Computational Intelligence & Communication Technology.