We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.
@article{arxiv.2004.10663,
title = {Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition},
author = {Dingmin Wang and Chenghua Lin and Qi Liu and Kam-Fai Wong},
journal= {arXiv preprint arXiv:2004.10663},
year = {2021}
}