fixed validation loop

Author: joel-huang

Diff for: .gitignore

@@ -1,4 +1,5 @@
 .ipynb_checkpoints/
 __pycache__/
 saved_models/
+*.ipynb
 *.pt

Diff for: README.md

@@ -1,39 +1,40 @@
-# Zero-shot User Intent Detection via Capsule Neural Networks (PyTorch Implementation)
+# GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks 
 
-This repository implements a capsule model named IntentCapsNet-ZSL on the SNIPS-NLU dataset with PyTorch (extension of Tensorflow version)
+This repository implements a capsule model IntentCapsNet-ZSL on the SNIPS-NLU dataset in Python 3
+with PyTorch, first introduced in the paper _Zero-shot User Intent Detection via Capsule Neural Networks_.
 
-The official Tensorflow version is available: 
-https://github.com/congyingxia/ZeroShotCapsule 
+The code aims to follow PyTorch best practices, using `torch` instead of `numpy` where possible, and using
+`.cuda()` for GPU computation. Feel free to contribute via pull requests.
 
-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)
+# Requirements
 
-https://arxiv.org/abs/1809.00385 
+python 3.6+
 
+torch 1.0.1
 
+numpy
 
-# Requirements
+gensim
 
-Python 2.7.12
+scikit-learn
 
-torch 1.0.1
+# Usage and Modification
 
-Numpy
+* To run the training-validation loop: `python run.py`.
+* The custom `Dataset` class is implemented in `dataset.py`.
 
-Gensim
+# Acknowledgements
+* Original repository (TensorFlow, Python 2): https://github.com/congyingxia/ZeroShotCapsule 
+* Re-implementation (PyTorch, Python 2): https://github.com/nhhoang96/ZeroShotCapsule-PyTorch-
 
-Sklearn
+Please see the following paper for the details:
 
-# Usage
+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.
 
-```
-python main.py
-```
+https://arxiv.org/abs/1809.00385 
 
-If you find the code useful, please cite the paper.
 
 ```
 @article{xia2018zero,
@@ -43,11 +44,7 @@ If you find the code useful, please cite the paper.
   year={2018}
 }
 ```
-
-# Acknowledgements
-https://github.com/congyingxia/ZeroShotCapsule
-
-https://github.com/soskek/dynamic_routing_between_capsules
-
-https://github.com/ExplorerFreda/Structured-Self-Attentive-Sentence-Embedding 
+# References
+* https://github.com/soskek/dynamic_routing_between_capsules
+* https://github.com/ExplorerFreda/Structured-Self-Attentive-Sentence-Embedding