Multi-domain Dialog State Tracking using Recurrent Neural Networks

By Nikola Mrksic, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Pei-hao Su, David Vandyke, Tsung-Hsien Wen, Susannah Young. 2015

189 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Model Architectures, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Richard Socher
  3. Caiming Xiong
  4. Mohit Bansal
  5. Percy Liang
  6. Jason Aaron Edward Weston
  7. Luke S. Zettlemoyer
  8. Yoshua Bengio

In Model Architectures

  1. Richard Socher
  2. Caiming Xiong
  3. Lina Maria Rojas-Barahona
  4. Dilek Z. Hakkani-Tür
  5. Xi Victoria Lin
  6. Kun Qian
  7. Rui Zhang
  8. Tsung-Hsien Wen

In Dialogue & Conversational AI

  1. Susannah Young
  2. Milica Gasic
  3. Pei-hao Su
  4. Tsung-Hsien Wen
  5. Blaise Thomson
  6. Matthew Henderson
  7. Nikola Mrksic
  8. Stefan Ultes

Citations in the corpus