Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking
arXiv:2106.08723
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%.
arXiv commentAccepted by Interspeech2021
References in corpus (4)
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
- Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
- MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation
- TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking