An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog

Abstract

We present a novel end-to-end trainable neural network model for task-oriented dialog systems. The model is able to track dialog state, issue API calls to knowledge base (KB), and incorporate structured KB query results into system responses to successfully complete task-oriented dialogs. The proposed model produces well-structured system responses by jointly learning belief tracking and KB result processing conditioning on the dialog history. We evaluate the model in a restaurant search domain using a dataset that is converted from the second Dialog State Tracking Challenge (DSTC2) corpus. Experiment results show that the proposed model can robustly track dialog state given the dialog history. Moreover, our model demonstrates promising results in producing appropriate system responses, outperforming prior end-to-end trainable neural network models using per-response accuracy evaluation metrics.

arXiv commentPublished at Interspeech 2017

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Recurrent Neural Network Regularization
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• Query-Reduction Networks for Question Answering
• Learning End-to-End Goal-Oriented Dialog
• Gated End-to-End Memory Networks

Cited by in corpus (18)

• End-to-End Task-Completion Neural Dialogue Systems
• End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
• Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation
• Dialog State Tracking: A Neural Reading Comprehension Approach
• Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
• Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models
• Sentiment Adaptive End-to-End Dialog Systems
• Deploying Lifelong Open-Domain Dialogue Learning
• Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation
• Improving Dialogue State Tracking by Discerning the Relevant Context
• A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems
• A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
• Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
• NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback
• Generative Dialog Policy for Task-oriented Dialog Systems
• Reinforced Natural Language Interfaces via Entropy Decomposition