Multi-domain Dialog State Tracking using Recurrent Neural Networks

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)  
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, welldefined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domainspecific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new
more » ... mains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.
doi:10.3115/v1/p15-2130 dblp:conf/acl/MrksicSTGSVWY15 fatcat:zic6tg2c7jfpjdro347ybectxm