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

TL;DR

This paper introduces an end-to-end neural network for task-oriented dialogs that effectively tracks dialog state, queries knowledge bases, and generates structured responses, improving over previous models in accuracy and robustness.

Contribution

The paper presents a novel neural network model that jointly learns belief tracking and KB query integration for task-oriented dialog systems.

Findings

Robust dialog state tracking demonstrated in restaurant search domain.

Outperforms prior end-to-end neural models in response accuracy.

Successfully integrates structured KB results into system responses.

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.