Out-of-Task Training for Dialog State Tracking Models
This work addresses the data sparsity problem for dialog state tracking models, which is a common bottleneck in dialog systems.
Dialog state tracking (DST) models suffer from data sparsity. This paper demonstrates the successful use of non-dialog data from unrelated NLP tasks to train DST models, leveraging external corpora to address the data scarcity.
Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data and by the specificity of dialog applications. In this work, we successfully utilize non-dialog data from unrelated NLP tasks to train dialog state trackers. This opens the door to the abundance of unrelated NLP corpora to mitigate the data sparsity issue inherent to DST.