Multilingual semantic parsing and code-switching

Long Duong, Hadi Afshar, Dominique Estival, Glen Pink, Philip Raymond Cohen, Mark Johnson

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-tosequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7% for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on codeswitching utterances which contain a mixture of English and German, even though the training data does not contain any code-switching. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3% accuracy on this dataset.
Original languageEnglish
Title of host publicationCoNLL 2017 - The 21st Conference on Computational Natural Language Learning - Proceedings of the Conference
Subtitle of host publicationAugust 3 - August 4, 2017 Vancouver, Canada
EditorsRoger Levy, Lucia Specia
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages379-389
Number of pages11
ISBN (Electronic)9781945626548
Publication statusPublished - Aug 2017
Externally publishedYes
EventConference on Natural Language Learning 2017 - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017
Conference number: 21st
http://www.conll.org/2017
https://www.aclweb.org/anthology/volumes/K17-1/ (Proceedings)

Conference

ConferenceConference on Natural Language Learning 2017
Abbreviated titleCoNLL 2017
CountryCanada
CityVancouver
Period3/08/174/08/17
Internet address

Keywords

  • semantic parsing
  • multilingual
  • code switching
  • deep learning

Cite this