End-to-End Task-Completion Neural Dialogue Systems

Abstract

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues. Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

11 pages, IJCNLP 2017, arXiv admin note: substantial text overlap with arXiv:1703.07055

References in corpus (3)

• Deep Reinforcement Learning for Dialogue Generation
• Continuously Learning Neural Dialogue Management
• An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog

Cited by in corpus (20)

• Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation
• Deep Conversational Recommender in Travel
• Budgeted Policy Learning for Task-Oriented Dialogue Systems
• Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use
• End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
• MOSS: End-to-End Dialog System Framework with Modular Supervision
• Unsupervised Learning of KB Queries in Task-Oriented Dialogs
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
• An Overview of Natural Language State Representation for Reinforcement Learning
• How to Evaluate Your Dialogue Models: A Review of Approaches
• DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues
• NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback
• Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning
• Towards Emotion-Aware User Simulator for Task-Oriented Dialogue
• Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective
• Conversational Query Rewriting with Self-supervised Learning
• Building A User-Centric and Content-Driven Socialbot
• A Corpus-free State2Seq User Simulator for Task-oriented Dialogue
• Iterative Delexicalization for Improved Spoken Language Understanding