Generative Adversarial Networks for text using word2vec intermediaries
Computation and Language
2019-04-05 v1 Artificial Intelligence
Machine Learning
Abstract
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the discrete nature of text, during training, using word embeddings. Our method is agnostic to vocabulary size and achieves competitive results relative to methods with various discrete gradient estimators.
Cite
@article{arxiv.1904.02293,
title = {Generative Adversarial Networks for text using word2vec intermediaries},
author = {Akshay Budhkar and Krishnapriya Vishnubhotla and Safwan Hossain and Frank Rudzicz},
journal= {arXiv preprint arXiv:1904.02293},
year = {2019}
}