Latent Intention Dialogue Models

2017/05/29 by Tsung-Hsien Wen, Wen, Tsung-Hsien, Yishu Miao +5 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1705.10229

openalex publication_date 2017/05/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• A Neural Conversational Model
• Stochastic Backpropagation and Approximate Inference in Deep Generative\n Models
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Long Short-Term Memory
• Neural Responding Machine for Short-Text Conversation
• On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
• Deep Reinforcement Learning for Dialogue Generation
• Dialogue Learning With Human-In-The-Loop

Cited by

• Latent Topic Conversational Models
• Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation

Related

• Hierarchical Text Generation and Planning for Strategic Dialogue
• Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
• Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue
• LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue\n Policy Optimization
• Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models