Towards Universal Dialogue State Tracking

TL;DR

This paper introduces StateNet, a universal dialogue state tracker that is scalable, adaptable to dynamic slot values, and leverages pre-trained word vectors, significantly improving over existing methods.

Contribution

StateNet is a novel, scalable dialogue state tracking model that shares parameters across slots and uses pre-trained embeddings, addressing key limitations of prior approaches.

Findings

Outperforms state-of-the-art methods on two datasets

Handles dynamic slot values without retraining

Reduces model complexity by sharing parameters

Abstract

Dialogue state tracking is the core part of a spoken dialogue system. It estimates the beliefs of possible user's goals at every dialogue turn. However, for most current approaches, it's difficult to scale to large dialogue domains. They have one or more of following limitations: (a) Some models don't work in the situation where slot values in ontology changes dynamically; (b) The number of model parameters is proportional to the number of slots; (c) Some models extract features based on hand-crafted lexicons. To tackle these challenges, we propose StateNet, a universal dialogue state tracker. It is independent of the number of values, shares parameters across all slots, and uses pre-trained word vectors instead of explicit semantic dictionaries. Our experiments on two datasets show that our approach not only overcomes the limitations, but also significantly outperforms the performance of state-of-the-art approaches.