Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization
Abstract
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should fully utilize information across all domains. One existing approach solves the problem by conducting multi-domain learning, using shared parameters for joint training across domains. We propose to improve the parameterization of this method by using domain-specific and task-specific model parameters to improve knowledge learning and transfer. Experiments on 5 domains show that our model is more effective for multi-domain SLU and obtain the best results. In addition, we show its transferability by outperforming the prior best model by 12.4\% when adapting to a new domain with little data.
Cite
@article{arxiv.2004.14871,
title = {Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization},
author = {Libo Qin and Minheng Ni and Yue Zhang and Wanxiang Che and Yangming Li and Ting Liu},
journal= {arXiv preprint arXiv:2004.14871},
year = {2021}
}
Comments
Accepted by Transactions on Asian and Low-Resource Language Information Processing (TALLIP)