TY - GEN
T1 - Capturing dialogue state variable dependencies with an energy-based neural dialogue state tracker
AU - Trinh, Anh Duong
AU - Ross, Robert J.
AU - Kelleher, John D.
N1 - Publisher Copyright:
©2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - Dialogue state tracking requires the population and maintenance of a multi-slot frame representation of the dialogue state. Frequently, dialogue state tracking systems assume independence between slot values within a frame. In this paper we argue that treating the prediction of each slot value as an independent prediction task may ignore important associations between the slot values, and, consequently, we argue that treating dialogue state tracking as a structured prediction problem can help to improve dialogue state tracking performance. To support this argument, the research presented in this paper is structured into three stages: (i) analyzing variable dependencies in dialogue data; (ii) applying an energy-based methodology to model dialogue state tracking as a structured prediction task; and (iii) evaluating the impact of inter-slot relationships on model performance. Overall, we demonstrate that modelling the associations between target slots with an energy-based formalism improves dialogue state tracking performance in a number of ways.
AB - Dialogue state tracking requires the population and maintenance of a multi-slot frame representation of the dialogue state. Frequently, dialogue state tracking systems assume independence between slot values within a frame. In this paper we argue that treating the prediction of each slot value as an independent prediction task may ignore important associations between the slot values, and, consequently, we argue that treating dialogue state tracking as a structured prediction problem can help to improve dialogue state tracking performance. To support this argument, the research presented in this paper is structured into three stages: (i) analyzing variable dependencies in dialogue data; (ii) applying an energy-based methodology to model dialogue state tracking as a structured prediction task; and (iii) evaluating the impact of inter-slot relationships on model performance. Overall, we demonstrate that modelling the associations between target slots with an energy-based formalism improves dialogue state tracking performance in a number of ways.
KW - dialogue state tracking
KW - multi-slot frame representation
KW - variable dependencies
KW - energy-based methodology
KW - structured prediction
KW - inter-slot relationships
UR - https://www.scopus.com/pages/publications/85091583919
U2 - 10.21427/ws3c-0s93
DO - 10.21427/ws3c-0s93
M3 - Conference contribution
AN - SCOPUS:85091583919
T3 - SIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference
SP - 75
EP - 84
BT - SIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2019
Y2 - 11 September 2019 through 13 September 2019
ER -