Neural_Machine_Translator_seq2seq

KO | EN

gitlite — search

#hacktoberfest #react #typescript #llm #machine-learning #rust #docker #nodejs #windows #cli #vue #security #ios #openai

Neural_Machine_Translator_seq2seq

(★ 13)

Neural Machine Translator for translating from english to hindi text. Used Pytorch framework with seq2seq architecture having Attention functionality

Neural_Machine_Translator_seq2seq Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Neural_Machine_Translator_seq2seq
Neural Machine Translator (NMT) for translating from english to hindi text. Used Pytorch framework with seq2seq architecture having Attention functionality . 
The Jupyter Notebook given in this repository is self explanatory and well documented.

![](https://cdn-images-1.medium.com/max/1600/1*75Jb0q3sX1GDYmJSfl-gOw.gif)

# Dependencies
Pytorch == 0.3.0 
Numpy == 1.14.2

[This](https://medium.com/@umerfarooq_26378/neural-machine-translation-with-code-68c425044bbd) blog explains NMT really well !

# Dataset
There are various sources from where you can download the eng-hind.txt parallel corpus : - 
1. [IIT-Bombay Dataset](http://www.cfilt.iitb.ac.in/iitb_parallel/iitb_corpus_download/) 
2. [HindEnCorp 0.5](https://lindat.mff.cuni.cz/repository/xmlui/handle/11858/00-097C-0000-0023-625F-0) 
3. [Indian parallel Corpora](https://github.com/joshua-decoder/indian-parallel-corpora)

The dataset file should be a tab seperated file having text in the following way - 
I am cold. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; मुझे ठंड लग रही है। 
My name is yash &nbsp;&nbsp; मेरा नाम यश है 
. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; . 
. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .

The jupyter notebook given here is for educational purpose, and if you wish to see some good results then I would highly recommend you to git clone one of the following repositories -

1.[Stanford NMT](https://nlp.stanford.edu/projects/nmt/) [Matlab] 
2.[tf-seq2seq](https://github.com/google/seq2seq) [TensorFlow] 
3.[Nemantus](https://github.com/rsennrich/nematus) [Theano] 
4.[OpenNMT](https://github.com/OpenNMT/OpenNMT) [Torch with Lua Language]---> Highly recommended, incorporates all the functionalities 
5.[OpenNMT-py](https://github.com/OpenNMT/OpenNMT-py) [PyTorch]

# Papers
A Statistical Approach to Machine Translation, 1990. 
Review Article: Example-based Machine Translation, 1999. 
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, 2014. 
Neural Machine Translation by Jointly Learning to Align and Translate, 2014. 
Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, 2016. 
Sequence to sequence learning with neural networks, 2014. 
Recurrent Continuous Translation Models, 2013. 
Continuous space translation models for phrase-based statistical machine translation, 2013.

# Acknowledgements
A big Thank you to the whole team of [Messy Fractals](https://messyfractals.wordpress.com/), especially [Dhanya P](https://www.linkedin.com/in/dhanyap/?originalSubdomain=in) and [Arvind Sivdas](https://www.linkedin.com/in/arvindsivdas/?originalSubdomain=in) for letting me work under them, for this project .

# References
The credits for this code go to the user [spro](https://github.com/spro/practical-pytorch/blob/master/seq2seq-translation/seq2seq-translation.ipynb). I have merely made some changes in it for dealing with Hindi text.

Neural_Machine_Translator_seq2seq

Neural_Machine_Translator_seq2seq Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Neural_Machine_Translator_seq2seq

Neural_Machine_Translator_seq2seq Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README