Zero-shot User Intent Detection via Capsule Neural Networks

This repository implements a capsule model named IntentCapsNet-ZSL on the SNIPS-NLU dataset with Tensorflow.

Please see the following paper for the details:

Congying Xia*, Chenwei Zhang*, Xiaohui Yan, Yi Chang, Philip S. Yu. Zero-shot User Intent Detection via Capsule Neural Networks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018. (* equally contributed)

https://arxiv.org/abs/1809.00385

Requirements

Python 2.7.12

Tensorflow 1.6.0

Numpy

Gensim

Sklearn

Usage

python main.py

If you find our code useful, please cite our paper.

@article{xia2018zero,
  title={Zero-shot User Intent Detection via Capsule Neural Networks},
  author={Xia, Congying and Zhang, Chenwei and Yan, Xiaohui and Chang, Yi and Yu, Philip S},
  journal={arXiv preprint arXiv:1809.00385},  
  year={2018}
}

Pytorch Version

A pytorch version can be found here: https://github.com/nhhoang96/ZeroShotCapsule-PyTorch-

Thanks to Hoang Nguyen @nhhoang96.

Acknowledgements

https://github.com/soskek/dynamic_routing_between_capsules

https://github.com/flrngel/Self-Attentive-tensorflow