Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation (2018-02-05T00:00:00.000000Z)

TL;DR

A novel language-model based discriminator is proposed, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators.

Abstract

Existing text generation methods tend to produce repeated and ”boring” expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.

Authors

Xu Sun

14 papers

Jingjing Xu

7 papers

Junyang Lin

6 papers

TL;DR

Abstract

Authors

References35 items

An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation

A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation

Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization

Global Encoding for Abstractive Summarization

Bag-of-Words as Target for Neural Machine Translation

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach

Table-to-text Generation by Structure-aware Seq2seq Learning

Generating Sentences by Editing Prototypes

Wasserstein Generative Adversarial Networks

BEGAN: Boundary Equilibrium Generative Adversarial Networks

Improved Training of Wasserstein GANs

Adversarial Learning for Neural Dialogue Generation

Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

Energy-based Generative Adversarial Network

An Actor-Critic Algorithm for Sequence Prediction

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Improved Techniques for Training GANs

f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

Sequence Level Training with Recurrent Neural Networks

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

A Diversity-Promoting Objective Function for Neural Conversation Models

Effective Approaches to Attention-based Neural Machine Translation

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

A Hierarchical Neural Autoencoder for Paragraphs and Documents

Sequence to Sequence Learning with Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

Policy Gradient Methods for Reinforcement Learning with Function Approximation

GENERATIVE ADVERSARIAL NETS

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Field of Study

Venue Information

Name

Type

URL

Alternate Names