Adversarial Learning for Neural Dialogue Generation (2017-01-23T00:00:00.000000Z)

TL;DR

This work applies adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances, and investigates models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls.

Abstract

We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we jointly train two systems: a generative model to produce response sequences, and a discriminator—analagous to the human evaluator in the Turing test— to distinguish between the human-generated dialogues and the machine-generated ones. In this generative adversarial network approach, the outputs from the discriminator are used to encourage the system towards more human-like dialogue. Further, we investigate models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines

Authors

Dan Jurafsky

15 papers

Jiwei Li

2 papers

Will Monroe

3 papers

TL;DR

Abstract

Authors

References52 items

Generating Long and Diverse Responses with Neural Conversation Models

Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses

Adversarial Evaluation of Dialogue Models

Aspect-augmented Adversarial Networks for Domain Adaptation

Deep Active Learning for Dialogue Generation

Online Sequence-to-Sequence Reinforcement Learning for Open-Domain Conversational Agents

A Simple, Fast Diverse Decoding Algorithm for Neural Generation

Generative Deep Neural Networks for Dialogue: A Short Review

Professor Forcing: A New Algorithm for Training Recurrent Networks

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

Strategy and Policy Learning for Non-Task-Oriented Conversational Systems

An Actor-Critic Algorithm for Sequence Prediction

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Improved Techniques for Training GANs

Continuously Learning Neural Dialogue Management

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

Deep Reinforcement Learning for Dialogue Generation

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

Sequence-to-Sequence Learning as Beam-Search Optimization

On the Evaluation of Dialogue Systems with Next Utterance Classification

Incorporating loose-structured knowledge into conversation modeling via recall-gate LSTM

Incorporating Loose-Structured Knowledge into LSTM with Recall Gate for Conversation Modeling

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

A Network-based End-to-End Trainable Task-oriented Dialogue System

LSTM based Conversation Models

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

A Persona-Based Neural Conversation Model

Mastering the game of Go with deep neural networks and tree search

Minimum Risk Training for Neural Machine Translation

Sequence Level Training with Recurrent Neural Networks

Generating Sentences from a Continuous Space

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Attention with Intention for a Neural Network Conversation Model

A Diversity-Promoting Objective Function for Neural Conversation Models

A Neural Attention Model for Abstractive Sentence Summarization

Effective Approaches to Attention-based Neural Machine Translation

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

A Neural Conversational Model

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

A Hierarchical Neural Autoencoder for Paragraphs and Documents

Neural Responding Machine for Short-Text Conversation

Sequence to Sequence Learning with Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Data-Driven Response Generation in Social Media

Learning to classify text using support vector machines - methods, theory and algorithms

Long Short-Term Memory

Likelihood ratio gradient estimation for stochastic systems

Computing Machinery and Intelligence

GENERATIVE ADVERSARIAL NETS

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Stochastic Optimization

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names