Skip to content

📄Neural Sentential Paraphrase Generation to Augment Chatbot Training Dataset

Notifications You must be signed in to change notification settings

vincent9514/Text-Variant-Generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Paraphraser

This project providers users the ability to do paraphrase generation for sentences through a clean and simple API. A demo can be seen here: pair-a-phrase

The paraphraser was developed under the Insight Data Science Artificial Intelligence program.

Model

The underlying model is a bidirectional LSTM encoder and LSTM decoder with attention trained using Tensorflow. Downloadable link here: paraphrase model

Prerequisiteis

  • python 3.5
  • Tensorflow 1.4.1
  • spacy

Inference Execution

Download the model checkpoint from the link above and run:

python inference.py --checkpoint=<checkpoint_path/model-171856>

Datasets

The dataset used to train this model is an aggregation of many different public datasets. To name a few:

  • para-nmt-5m
  • Quora question pair
  • SNLI
  • Semeval
  • And more!

I have not included the aggregated dataset as part of this repo. If you're curious and would like to know more, contact me. Pretrained embeddings come from John Wieting's para-nmt-50m project.

Training

Training was done for 2 epochs on a Nvidia GTX 1080 and evaluted on the BLEU score. The Tensorboard training curves can be seen below. The grey curve is train and the orange curve is dev.

TODOs

  • pip installable package
  • Explore deeper number of layers
  • Recurrent layer dropout
  • Greater dataset augmentation
  • Try residual layer
  • Model compression
  • Byte pair encoding for out of set vocabulary

Citations

@inproceedings { wieting-17-millions, 
    author = {John Wieting and Kevin Gimpel}, 
    title = {Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations}, 
    booktitle = {arXiv preprint arXiv:1711.05732}, year = {2017} 
}

@inproceedings { wieting-17-backtrans, 
    author = {John Wieting, Jonathan Mallinson, and Kevin Gimpel}, 
    title = {Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext}, 
    booktitle = {Proceedings of Empirical Methods in Natural Language Processing}, 
    year = {2017} 
}

About

📄Neural Sentential Paraphrase Generation to Augment Chatbot Training Dataset

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages