Latent Intention Dialogue Models

Abstract

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture natural conversational variability. In this paper, we propose a Latent Intention Dialogue Model (LIDM) that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. In a goal-oriented dialogue scenario, these latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experimental evaluation of LIDM shows that the model out-performs published benchmarks for both corpus-based and human evaluation, demonstrating the effectiveness of discrete latent variable models for learning goal-oriented dialogues.

Accepted at ICML 2017

References in corpus (9)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A Neural Conversational Model
• Deep Reinforcement Learning for Dialogue Generation
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Neural Responding Machine for Short-Text Conversation
• On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
• Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
• Dialogue Learning With Human-In-The-Loop
• Latent Variable Dialogue Models and their Diversity

Cited by in corpus (12)

• A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
• End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient
• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
• MALA: Cross-Domain Dialogue Generation with Action Learning
• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
• Decoupling Strategy and Generation in Negotiation Dialogues
• Teaching Machines to Converse
• Affective Neural Response Generation
• Latent Topic Conversational Models
• Cost-Based Goal Recognition Meets Deep Learning
• Incorporating Relevant Knowledge in Context Modeling and Response Generation
• Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation