Research project to apply Graph Convolution to NLP.

1. Why & What is Graph Convolution
2. Implementation of Graph Convolution: Graph Attention Network
3. Kinds of task in Graph
4. Case study to use Graph Convolution in NLP
5. Design of Experiment to verify effectiveness of Graph Convolution
6. Rethink the property of Graph Convolution and find appropriate task in NLP
7. Research summary of Graph Convolution in NLP

• Language Modeling
• Graph Attention Network Layer
  • Fix to support batch data
  • Experiment by existing dataset
  • What is really effective attention method on Graph?
• Graph Convolution for Text Classification
  • Prepare the Dataset
  • Make baseline model and analysis
  • Make graph convolution model
  • Analyze graph convolution model
  • Enhance graph convolution model

• How Powerful are Graph Neural Networks?