README.md

Domain Adaptation with Adversarial Training and Graph Embeddings

Please be patient, we are slowly uploading code and preparing readme file.

Introduction

This is forked form the implementation of Planetoid, a graph-based semi-supervised learning method proposed in the following paper: Revisiting Semi-Supervised Learning with Graph Embeddings. Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov., ICML 2016.

For the implementation with Domain Adaptation with Adversarial training, we significantly modified the code. Below, we provide the details.

We will make the code publicly available soon. Please be patient.

Prerequisites

• python 2.7
• gensim
• lasagne
• keras with tensorflow backend
• Please download Word2Vec model.

Data

Word2Vec Model

More details of this model can be found on github

Please download the model from CrisisNLP.

Models

Graph Embeddings

Domain Adaptation

How to Run

Please Cite the Following Paper

Firoj Alam, Shafiq Joty, Muhammad Imran. Domain Adaptation with Adversarial Training and Graph Embeddings. 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018, Melbourne, Australia.

@inproceedings{alam2016bidirectional,
  title={Domain Adaptation with Adversarial Training and Graph Embeddings},
  author={Firoj Alam, Shafiq Joty, Muhammad Imran},
  booktitle={56th Annual Meeting of the Association for Computational Linguistics (ACL)},
  year={2018},
  organization={ACL}
}