ONENET: Joint domain, intent, slot prediction for spoken language understanding

Young Bum Kim, Sungjin Lee, Karl Stratos

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

24 Scopus citations

Abstract

In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline approach, however, has some disadvantages: error propagation and lack of information sharing. To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions. Our approach adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task. With a few more ingredients, e.g. orthography-sensitive input encoding and curriculum training, our model delivered significant improvements in all three tasks across all domains over strong baselines, including one using oracle prediction for domain detection, on real user data of a commercial personal assistant.

Original languageEnglish (US)
Title of host publication2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages547-553
Number of pages7
ISBN (Electronic)9781509047888
DOIs
StatePublished - Jan 24 2018
Externally publishedYes
Event2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Okinawa, Japan
Duration: Dec 16 2017Dec 20 2017

Publication series

Name2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings
Volume2018-January

Conference

Conference2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017
CountryJapan
CityOkinawa
Period12/16/1712/20/17

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Keywords

  • Joint modeling
  • Multitask learning
  • Natural language understanding

Fingerprint Dive into the research topics of 'ONENET: Joint domain, intent, slot prediction for spoken language understanding'. Together they form a unique fingerprint.

Cite this