Skip to content

Library to train parallel-aligned sequence data based on Keras

Notifications You must be signed in to change notification settings

shashankg7/Seq2Seq

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Seq2Seq Keras

A general purpose library for training seq2seq models on a parallel corpus. No explicit programming is required, training script will take care of preprocessing the data, compiling the model and then training on the corpus. It's a general purpose library, so it can be used for different NLP tasks which requires seq2seq mapping like Text Summarization, Question Answering system, Chatbots etc.

Requirements

  • keras

  • numpy

  • theano/tensorflow

  • CUDA and CuDNN (if using GPU)

Example on Machine Translation

On Machine Translation task (translation from English to Hindi), after ~1000 epochs of training (less training data) it was giving following results:

nepal external ministry
नेपाली विदेश UNK

ramayana is an extraordinary epic poetry written by poet valmiki रामायण कवि वाल्मीकि द्वारा लिखा गया संस्कृत का एक अनुपम

he is the first black lrb UNK rrb president
वे इस देश के प्रथम UNK -LRB- अफ्रीकी UNK -RRB-

administrative divisions
प्रशासनिक विभाजन

TO-DO

  • Current parameters hard coded, add argument parser

  • Add model saving method

  • Add model loading method

About

Library to train parallel-aligned sequence data based on Keras

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published