# Generative Adversarial Networks for text using word2vec intermediaries

## TL;DR

This paper introduces a novel GAN-based method for text generation that leverages word embeddings to address the challenges of discrete data, achieving competitive results across different vocabulary sizes.

## Contribution

It presents a new approach using word2vec intermediaries to enable GAN training on text, which is a significant advancement over existing discrete gradient estimation methods.

## Key findings

- Achieves competitive text generation quality
- Handles large vocabularies effectively
- Demonstrates robustness across different datasets

## 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.