Adversarial Mutual Information for Text Generation

TL;DR

This paper introduces Adversarial Mutual Information (AMI), a novel framework for text generation that models both forward and backward mutual information to improve generation quality and dependency modeling.

Contribution

The paper proposes a new adversarial framework that jointly models forward and backward mutual information, enhancing text generation by promoting better source-target dependencies.

Findings

AMI outperforms strong baselines in various text generation tasks.

The framework achieves a tighter lower bound of mutual information.

Latent noise sampling improves long-term dependency in generated text.

Abstract

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.