Paper: IBM's Belief Tracker: Results On Dialog State Tracking Challenge Datasets

ACL ID W14-0202
Title IBM's Belief Tracker: Results On Dialog State Tracking Challenge Datasets
Venue EACL Workshop on Dialogue in Motion
Session
Year 2014
Authors

Accurate dialog state tracking is crucial for the design of an efficient spoken dialog system. Until recently, quantitative com- parison of different state tracking meth- ods was difficult. However the 2013 Dia- log State Tracking Challenge (DSTC) in- troduced a common dataset and metrics that allow to evaluate the performance of trackers on a standardized task. In this pa- per we present our belief tracker based on the Hidden Information State (HIS) model with an adjusted user model component. Further, we report the results of our tracker on test3 dataset from DSTC. Our tracker is competitive with trackers submitted to DSTC, even without training it achieves the best results in L2 metrics and it per- forms between second and third place in accuracy. After adjusting the tracker using the p...