Document Type
Conference Paper
Rights
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Disciplines
Computer Sciences
Abstract
The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing. To improve state tracking quality, we argue that relationships between different aspects of dialogue state must be taken into account as they can often guide a more accurate interpretation process. To this end, we present an energy-based approach to dialogue state tracking as a structured classification task. The novelty of our approach lies in the use of an energy network on top of a deep learning architecture to explore more signal correlations between network variables including input features and output labels. We demonstrate that the energy-based approach improves the performance of a deep learning dialogue state tracker towards state-of-the-art results without the need for many of the other steps required by current state-of-the-art methods.
DOI
https://doi.org/10.18653/v1/W19-4109
Recommended Citation
Trinh, A., Ross, R.J. & Kelleher, J.D. (2019) Energy-Based Modelling for Dialogue State Tracking, 1st Workshop on NLP for Conversational AI,Florence, Italy, 1st August, 2019. doi:10.18653/v1/W19-4109
Funder
Science Foundation Ireland, European Regional Development Fund (ERDF)
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Publication Details
The 1st Workshop on NLP for Conversational AI