Domain attention with an ensemble of experts

Young Bum Kim, Karl Stratos, Dongchan Kim

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

28 Scopus citations

Abstract

An important problem in domain adaptation is to quickly generalize to a new domain with limited supervision given K existing domains. One approach is to retrain a global model across all K + 1 domains using standard techniques, for instance Daumé III (2009). However, it is desirable to adapt without having to re-estimate a global model from scratch each time a new domain with potentially new intents and slots is added. We describe a solution based on attending an ensemble of domain experts. We assume K domain-specific intent and slot models trained on respective domains. When given domain K + 1, our model uses a weighted combination of the K domain experts' feedback along with its own opinion to make predictions on the new domain. In experiments, the model significantly outperforms baselines that do not use domain adaptation and also performs better than the full retraining approach.

Original languageEnglish (US)
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages643-653
Number of pages11
ISBN (Electronic)9781945626753
DOIs
StatePublished - 2017
Externally publishedYes
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: Jul 30 2017Aug 4 2017

Publication series

NameACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period7/30/178/4/17

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Artificial Intelligence
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Domain attention with an ensemble of experts'. Together they form a unique fingerprint.

Cite this