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

2016/04/15 by Tsung-Hsien Wen, Wen, Tsung-Hsien, David Vandyke +13 · 27 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #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.1604.04562

openalex publication_date 2016/04/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Citations

• Neural Responding Machine for Short-Text Conversation
• Latent Predictor Networks for Code Generation
• On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems

Cited by

• Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
• Closing the Expression Gap in LLM Instructions via Socratic Questioning
• DyBBT: Dynamic Balance via Bandit inspired Targeting for Dialog Policy with Cognitive Dual-Systems
• Rasa: Open Source Language Understanding and Dialogue Management
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• Evaluating, Synthesizing, and Enhancing for Customer Support Conversation
• Interactive Classification by Asking Informative Questions
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Zero-Shot Dialog Generation with Cross-Domain Latent Actions
• STN4DST: A Scalable Dialogue State Tracking based on Slot Tagging Navigation
• Dialog state tracking, a machine reading approach using Memory Network
• Personalizing a Dialogue System with Transfer Reinforcement Learning
• Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
• End to End Dialogue Transformer
• Unsupervised Text Style Transfer using Language Models as Discriminators
• Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• Adversarial Learning for Neural Dialogue Generation
• KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System
• Deep Reinforcement Learning for Dialogue Generation
• Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems
• Multipurpose Intelligent Process Automation via Conversational Assistant
• MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
• Data Augmentation for Copy-Mechanism in Dialogue State Tracking
• Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction

Related

• End-to-end Conversation Modeling Track in DSTC6
• Task-Oriented Dialogue with In-Context Learning
• Deploying a Retrieval based Response Model for Task Oriented Dialogues
• Training Neural Response Selection for Task-Oriented Dialogue Systems
• Teaching Machines to Converse