https://github.com/taolei87/rcnn

Recurrent & convolutional neural network modules
https://github.com/taolei87/rcnn

Last synced: 5 days ago
JSON representation

Recurrent & convolutional neural network modules

• Host: GitHub
• URL: https://github.com/taolei87/rcnn
• Owner: taolei87
• License: apache-2.0
• Created: 2015-12-17T02:34:28.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2018-08-16T21:40:05.000Z (over 6 years ago)
• Last Synced: 2024-12-24T05:07:12.604Z (12 days ago)
• Language: Python
• Homepage:
• Size: 113 MB
• Stars: 355
• Watchers: 23
• Forks: 129
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
### Latest updates

Check [code/rationale](/code/rationale) for the project of learning rationales for neural prediction:  


         

[Adam Yala](https://github.com/yala/) has implemented a **Pytorch** version of the rationale project! 

Check it out at: https://github.com/yala/text_nn



-------

#### About this repo

This repo contains Theano implementations of popular neural network components and optimization methods. Source code of the following papers are also available:

  [1] [Molding CNNs for text: non-linear, non-consecutive convolutions](http://arxiv.org/abs/1508.04112). EMNLP 2015

  

  [2] [Semi-supervised Question Retrieval with Gated Convolutions](http://arxiv.org/abs/1512.05726). NAACL 2016

  [3] [Rationalizing Neural Predictions](https://people.csail.mit.edu/taolei/papers/emnlp16_rationale.pdf). EMNLP 2016

#### Features

  - Basic modules including feedforward layer, dropout, word embedding, RNN, LSTM, GRU and CNN

  - Optimization methods including SGD, AdaGrad, AdaDelta and Adam

  - Advanced modules from recent papers such as attention and gated convolution.

  - Transparent to use GPU

-------

#### Projects

###### 1. Neural question retrieval for community-based QA

The directories [code/qa](/code/qa) and [code/pt](/code/pt) contain the implementation of the model described in paper [[2]](http://arxiv.org/abs/1512.05726). Datasets and and pre-trained word vectors are available at [here](https://github.com/taolei87/askubuntu).

###### 2. Sentiment analysis / document classification

The directory [code/sentiment](/code/sentiment) contains the implementation of the model described in paper [[1]](http://arxiv.org/abs/1508.04112). Datasets and and pre-trained word vectors are available at [here](https://github.com/taolei87/text_convnet).

###### 3. Rationalizing neural predictions

The directory [code/rationale](/code/rationale) contains the implementation of the model described in paper [[3]](https://people.csail.mit.edu/taolei/papers/emnlp16_rationale.pdf).

-------

#### Dependencies

  [Theano](http://deeplearning.net/software/theano/) >= 0.7, Python >= 2.7, Numpy

-------