Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking

TL;DR

This paper introduces Coreference Dialogue State Tracker (CDST), a novel model that explicitly incorporates coreference features to improve dialogue state tracking in multi-turn task-oriented dialogues, achieving state-of-the-art accuracy.

Contribution

The paper proposes a new coreference-aware model for dialogue state tracking that explicitly models coreference phenomena to enhance performance.

Findings

Achieves state-of-the-art joint goal accuracy of 56.47% on MultiWOZ 2.1.

Effectively models coreference to improve dialogue understanding.

Outperforms existing DST models on multi-domain datasets.

Abstract

Dialogue State Tracking (DST), which is the process of inferring user goals by estimating belief states given the dialogue history, plays a critical role in task-oriented dialogue systems. A coreference phenomenon observed in multi-turn conversations is not addressed by existing DST models, leading to sub-optimal performances. In this paper, we propose Coreference Dialogue State Tracker (CDST) that explicitly models the coreference feature. In particular, at each turn, the proposed model jointly predicts the coreferred domain-slot pair and extracts the coreference values from the dialogue context. Experimental results on MultiWOZ 2.1 dataset show that the proposed model achieves the state-of-the-art joint goal accuracy of 56.47%.