Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation

Abstract

Training generative models that can generate high-quality text with sufficient diversity is an important open problem for Natural Language Generation (NLG) community. Recently, generative adversarial models have been applied extensively on text generation tasks, where the adversarially trained generators alleviate the exposure bias experienced by conventional maximum likelihood approaches and result in promising generation quality. However, due to the notorious defect of mode collapse for adversarial training, the adversarially trained generators face a quality-diversity trade-off, i.e., the generator models tend to sacrifice generation diversity severely for increasing generation quality. In this paper, we propose a novel approach which aims to improve the performance of adversarial text generation via efficiently decelerating mode collapse of the adversarial training. To this end, we introduce a cooperative training paradigm, where a language model is cooperatively trained with the generator and we utilize the language model to efficiently shape the data distribution of the generator against mode collapse. Moreover, instead of engaging the cooperative update for the generator in a principled way, we formulate a meta learning mechanism, where the cooperative update to the generator serves as a high level meta task, with an intuition of ensuring the parameters of the generator after the adversarial update would stay resistant against mode collapse. In the experiment, we demonstrate our proposed approach can efficiently slow down the pace of mode collapse for the adversarial text generators. Overall, our proposed method is able to outperform the baseline approaches with significant margins in terms of both generation quality and diversity in the testified domains.

References in corpus (23)

• Distilling the Knowledge in a Neural Network
• Sequence to Sequence Learning with Neural Networks
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Categorical Reparameterization with Gumbel-Softmax
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Deep Reinforcement Learning for Dialogue Generation
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Long Text Generation via Adversarial Training with Leaked Information
• Texygen: A Benchmarking Platform for Text Generation Models
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Adversarial Feature Matching for Text Generation
• Adversarial Generation of Natural Language
• Policy Distillation
• Language GANs Falling Short
• Adversarial Text Generation via Feature-Mover's Distance
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Neural Text Generation: Past, Present and Beyond
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• CoT: Cooperative Training for Generative Modeling of Discrete Data

Cited by in corpus (1)

• A survey on text generation using generative adversarial networks