Adversarial Ranking for Language Generation

Abstract

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than training the discriminator to learn and assign absolute binary predicate for individual data sample, the proposed RankGAN is able to analyze and rank a collection of human-written and machine-written sentences by giving a reference group. By viewing a set of data samples collectively and evaluating their quality through relative ranking scores, the discriminator is able to make better assessment which in turn helps to learn a better generator. The proposed RankGAN is optimized through the policy gradient technique. Experimental results on multiple public datasets clearly demonstrate the effectiveness of the proposed approach.

arXiv commentNIPS2017

References in corpus (8)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Image Captioning via Policy Gradient optimization of SPIDEr
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• On distinguishability criteria for estimating generative models

Cited by in corpus (50)

• How Generative Adversarial Networks and Their Variants Work: An Overview
• Long Text Generation via Adversarial Training with Leaked Information
• Survey on reinforcement learning for language processing
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Language GANs Falling Short
• On Leveraging Pretrained GANs for Generation with Limited Data
• Improving Sequence-to-Sequence Learning via Optimal Transport
• Neural Language Generation: Formulation, Methods, and Evaluation
• Semi-supervised Text Regression with Conditional Generative Adversarial Networks
• Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
• Jointly Measuring Diversity and Quality in Text Generation Models
• Self-Adversarial Learning with Comparative Discrimination for Text Generation
• Real-world Person Re-Identification via Degradation Invariance Learning
• Domain Adaptive Text Style Transfer
• Semantic Bottleneck Scene Generation
• Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach
• Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
• Rethinking Exposure Bias In Language Modeling
• Neural Topic Modeling with Bidirectional Adversarial Training
• Retrieval-Enhanced Adversarial Training for Neural Response Generation
• Open Event Extraction from Online Text using a Generative Adversarial Network
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• ARAML: A Stable Adversarial Training Framework for Text Generation
• Reward Constrained Interactive Recommendation with Natural Language Feedback
• Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
• Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
• TextBox: A Unified, Modularized, and Extensible Framework for Text Generation
• Text Generation with Exemplar-based Adaptive Decoding
• Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Learn distributed GAN with Temporary Discriminators
• Improving Text Generation with Student-Forcing Optimal Transport
• Towards Coherent and Cohesive Long-form Text Generation
• Controllable and Diverse Text Generation in E-commerce
• EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation
• Collaborative Training of GANs in Continuous and Discrete Spaces for Text Generation
• Distributional Discrepancy: A Metric for Unconditional Text Generation
• Towards Controllable and Personalized Review Generation
• Rational Recurrences
• ATM:Adversarial-neural Topic Model
• Generative Adversarial Networks for Annotated Data Augmentation in Data Sparse NLU
• Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
• Controlled AutoEncoders to Generate Faces from Voices
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence
• Adversarial Machine Learning in Text Analysis and Generation
• Efficient text generation of user-defined topic using generative adversarial networks
• Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?
• Evaluating Computational Language Models with Scaling Properties of Natural Language
• The Detection of Distributional Discrepancy for Text Generation
• TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation