Adversarial Generation of Natural Language
This work addresses the challenge of adversarial natural language generation for researchers in NLP, though it appears incremental as it builds on existing GAN frameworks with a new baseline method.
The paper tackled the problem of generating natural language using Generative Adversarial Networks (GANs), which lag behind likelihood-based methods, by introducing a simple baseline that addresses the discrete output space without gradient estimators, achieving state-of-the-art results on a Chinese poem generation dataset.
Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation. Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far behind likelihood based methods. In this paper, we take a step towards generating natural language with a GAN objective alone. We introduce a simple baseline that addresses the discrete output space problem without relying on gradient estimators and show that it is able to achieve state-of-the-art results on a Chinese poem generation dataset. We present quantitative results on generating sentences from context-free and probabilistic context-free grammars, and qualitative language modeling results. A conditional version is also described that can generate sequences conditioned on sentence characteristics.