The implementation of text classification using character level convoultion neural networks using Keras
Switch branches/tags
Nothing to show
Clone or download
mhjabreel Merge pull request #7 from chaitjo/master
Implemented Character-level TCN model from Bai et al., 2018
Latest commit 4f42df7 Aug 2, 2018

README.md

Character Level CNNs in Keras

This repository contains Keras implementations for Character-level Convolutional Neural Networks for text classification on AG's News Topic Classification Dataset.

The following models have been implemented:

  1. Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. NIPS 2015
  2. Yoon Kim, Yacine Jernite, David Sontag, Alexander M. Rush. Character-Aware Neural Language Models. AAAI 2016
  3. Shaojie Bai, J. Zico Kolter, Vladlen Koltun. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. ArXiv preprint (2018)

Kim's CharCNN was originally part of an end-to-end trained pipeline for language modelling, but has been adapted for text classification.

Usage

  1. Install dependencies (Tensorflow 1.3 and Keras 2.1.3):
$ pip install -r requirements.txt
  1. Specify the training and testing data sources and model hyperparameters in the config.json file.

  2. Run the main.py file as below:

$ python main.py --model [model_name]

Replace [model_name] with either zhang or kim to run the desired model.

Results

Coming soon.