Robust zero-shot cross-domain slot filling with example values

Darsh J. Shah, Raghav Gupta, Amir A. Fayazi, Dilek Hakkani-Tür

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains. Often, however, little to no target domain training data may be available, or the training and target domain schemas may be misaligned, as is common for web forms on similar websites. Prior zero-shot slot filling models use slot descriptions to learn concepts, but are not robust to misaligned schemas. We propose utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains and robust to misaligned schemas. Our approach outperforms state-ofthe-art models on two multi-domain datasets, especially in the low-data setting.

Original languageEnglish (US)
Title of host publicationACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages5484-5490
Number of pages7
ISBN (Electronic)9781950737482
StatePublished - 2020
Externally publishedYes
Event57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy
Duration: Jul 28 2019Aug 2 2019

Publication series

NameACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/TerritoryItaly
CityFlorence
Period7/28/198/2/19

ASJC Scopus subject areas

  • Language and Linguistics
  • General Computer Science
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Robust zero-shot cross-domain slot filling with example values'. Together they form a unique fingerprint.

Cite this