Change search
ReferencesLink to record
Permanent link

Direct link
Enriching the Swedish Sign Language Corpus with Part of Speech Tags Using Joint Bayesian Word Alignment and Annotation Transfer
Stockholm University, Faculty of Humanities, Department of Linguistics, Computational Linguistics.ORCID iD: 0000-0002-6027-4156
Stockholm University, Faculty of Humanities, Department of Linguistics, General Linguistics.ORCID iD: 0000-0001-7549-4648
Stockholm University, Faculty of Humanities, Department of Linguistics, Sign Language.ORCID iD: 0000-0001-9035-0669
2015 (English)In: Proceedings of the 20th Nordic Conference of Computational Linguistics: NODALIDA 2015, May 11-13, 2015, Vilnius, Lithuania / [ed] Beáta Megyesi, Linköping University Electronic Press, 2015, 263-268 p.Conference paper (Refereed)
Abstract [en]

We have used a novel Bayesian model of joint word alignment and part of speech (PoS) annotation transfer to enrich the Swedish Sign Language Corpus with PoS tags. The annotations were then hand-corrected in order to both improve annotation quality for the corpus, and allow the empirical evaluation presented herein.

Place, publisher, year, edition, pages
Linköping University Electronic Press, 2015. 263-268 p.
Series
, Linköping Electronic Conference Proceedings, ISSN 1650-3740 ; 109
Keyword [en]
sign language, bayesian models, part of speech tagging, pos tagging, transfer learning
National Category
General Language Studies and Linguistics Language Technology (Computational Linguistics)
Research subject
Sign Language
Identifiers
URN: urn:nbn:se:su:diva-117099ISBN: 978-91-7519-098-3OAI: oai:DiVA.org:su-117099DiVA: diva2:810265
Conference
20th Nordic Conference on Computational Linguistics, Vilnius, Lithuania, May 11-13, 2015
Available from: 2015-05-06 Created: 2015-05-06 Last updated: 2016-11-11Bibliographically approved

Open Access in DiVA

Enriching the Swedish Sign Language Corpus with Part of Speech Tags Using Joint Bayesian Word Alignment and Annotation Transfer(145 kB)83 downloads
File information
File name FULLTEXT01.pdfFile size 145 kBChecksum SHA-512
d5119b3330f5b1976129f7678bd4f207aac82013ade679fc077ad1e66cf3c13aafb9d4604150b34c66b527e90d1fc33c698323be049a6f02f938169452ad35d6
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Östling, RobertBörstell, CarlWallin, Lars
By organisation
Computational LinguisticsGeneral LinguisticsSign Language
General Language Studies and LinguisticsLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 83 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 287 hits
ReferencesLink to record
Permanent link

Direct link