Recurrent Polynomial Network for Dialogue State Tracking

TL;DR

This paper introduces a recurrent polynomial network (RPN) for dialogue state tracking, combining rule-based and statistical advantages, and demonstrates its superior performance on benchmark datasets.

Contribution

The paper proposes a novel RPN framework that enhances DST by integrating the benefits of CMBP with improved statistical properties.

Findings

RPN outperforms traditional rule-based methods.

RPN is competitive with advanced statistical approaches.

RPN shows significant improvements on DSTC datasets.

Abstract

Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses. Recent studies on constrained Markov Bayesian polynomial (CMBP) framework take the first step towards bridging the gap between rule-based and statistical approaches for DST. In this paper, the gap is further bridged by a novel framework -- recurrent polynomial network (RPN). RPN's unique structure enables the framework to have all the advantages of CMBP including efficiency, portability and interpretability. Additionally, RPN achieves more properties of statistical approaches than CMBP. RPN was evaluated on the data corpora of the second and the third Dialog State Tracking Challenge (DSTC-2/3). Experiments showed that RPN can significantly outperform both traditional rule-based approaches and statistical approaches with similar feature set. Compared with the state-of-the-art statistical DST approaches with a lot richer features, RPN is also competitive.