Robust Dialogue State Tracking with Weak Supervision and Sparse Data. (arXiv:2202.03354v2 [cs.CL] UPDATED)

Generalising dialogue state tracking (DST) to new data is especially
challenging due to the strong reliance on abundant and fine-grained supervision
during training. Sample sparsity, distributional shift and the occurrence of
new concepts and topics frequently lead to severe performance degradation
during inference. In this paper we propose a training strategy to build
extractive DST models without the need for fine-grained manual span labels. Two
novel input-level dropout methods mitigate the negative impact of sample
sparsity. We propose a new …

arxiv data state tracking