Robust Dialogue State Tracking with Weak Supervision and Sparse Data

Michael Heck, Nurul Lubis, Carel van Niekerk, Shutong Feng, Christian Geishauser, Hsien-Chin Lin, Milica Gašić


Abstract
Generalizing 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 model architecture with a unified encoder that supports value as well as slot independence by leveraging the attention mechanism. We combine the strengths of triple copy strategy DST and value matching to benefit from complementary predictions without violating the principle of ontology independence. Our experiments demonstrate that an extractive DST model can be trained without manual span labels. Our architecture and training strategies improve robustness towards sample sparsity, new concepts, and topics, leading to state-of-the-art performance on a range of benchmarks. We further highlight our model’s ability to effectively learn from non-dialogue data.
Anthology ID:
2022.tacl-1.68
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1175–1192
Language:
URL:
https://aclanthology.org/2022.tacl-1.68
DOI:
10.1162/tacl_a_00513
Bibkey:
Cite (ACL):
Michael Heck, Nurul Lubis, Carel van Niekerk, Shutong Feng, Christian Geishauser, Hsien-Chin Lin, and Milica Gašić. 2022. Robust Dialogue State Tracking with Weak Supervision and Sparse Data. Transactions of the Association for Computational Linguistics, 10:1175–1192.
Cite (Informal):
Robust Dialogue State Tracking with Weak Supervision and Sparse Data (Heck et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.68.pdf