Multi-domain Dialog State Tracking using Recurrent Neural Networks

Autor:	Mrkšić, Nikola, Séaghdha, Diarmuid Ó, Thomson, Blaise, Gašić, Milica, Su, Pei-Hao, Vandyke, David, Wen, Tsung-Hsien, Young, Steve
Rok vydání:	2015
Předmět:	Computer Science - Computation and Language Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined 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 domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model. Comment: Accepted as a short paper in the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1506.07190 Zobrazit plný text záznamu View this record from Arxiv