A Robust Data-Driven Approach for Dialogue State Tracking of Unseen Slot Values

TL;DR

This paper introduces a robust, data-driven dialogue state tracker that effectively handles unseen slot values using a copying mechanism, outperforming existing methods on benchmark datasets.

Contribution

It proposes a novel copying mechanism-based dialogue state tracker that can track unseen slot values without retraining, enhancing flexibility and performance.

Findings

Outperforms existing approaches on DSTC2, DSTC3, and WoZ2.0 datasets.

Effectively tracks unseen slot values without retraining.

Provides significant improvements in dialogue state modeling.

Abstract

A Dialogue State Tracker is a key component in dialogue systems which estimates the beliefs of possible user goals at each dialogue turn. Deep learning approaches using recurrent neural networks have shown state-of-the-art performance for the task of dialogue state tracking. Generally, these approaches assume a predefined candidate list and struggle to predict any new dialogue state values that are not seen during training. This makes extending the candidate list for a slot without model retaining infeasible and also has limitations in modelling for low resource domains where training data for slot values are expensive. In this paper, we propose a novel dialogue state tracker based on copying mechanism that can effectively track such unseen slot values without compromising performance on slot values seen during training. The proposed model is also flexible in extending the candidate list without requiring any retraining or change in the model. We evaluate the proposed model on various benchmark datasets (DSTC2, DSTC3 and WoZ2.0) and show that our approach, outperform other end-to-end data-driven approaches in tracking unseen slot values and also provides significant advantages in modelling for DST.