ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

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

Ting Han, Chongxuan Huang, Wei Peng

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 suboptimal 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%.


doi: 10.21437/Interspeech.2021-1463

Cite as: Han, T., Huang, C., Peng, W. (2021) Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking. Proc. Interspeech 2021, 1259-1263, doi: 10.21437/Interspeech.2021-1463

@inproceedings{han21_interspeech,
  author={Ting Han and Chongxuan Huang and Wei Peng},
  title={{Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1259--1263},
  doi={10.21437/Interspeech.2021-1463}
}