Change search
ReferencesLink to record
Permanent link

Direct link
From the extraction of continuous features in parallel texts to visual analytics of heterogeneous areal-typological datasets
Stockholm University, Faculty of Humanities, Department of Linguistics, General Linguistics.ORCID iD: 0000-0002-0256-6855
2014 (English)In: Language Processing and Grammars: The role of functionally oriented computational models / [ed] Brian Nolan & Carlos Periñán-Pascual, Amsterdam: John Benjamins Publishing Company, 2014, 13-38 p.Chapter in book (Refereed)
Abstract [en]

The aim of this paper is twofold. First, we show that functionally motivatedprocedural approaches may help to automatically extract typological featuresfrom texts. This idea is illustrated with measuring cross-linguistic variationin the domain of morphological typology based on parallel texts. Second, wedemonstrate that the methodology developed in the field of visual analyticsallows for detecting patterns or regularities in the automatically extractedfeatures. At the heart of our approach lies an extended sunburst visualization,which enables a cross-comparison of a large number of features within thecontext of language genealogy and areal information. We provide evidence of theusefulness of the present approach with case studies where the visualizations ofthe extracted features reveal interesting insights.

Place, publisher, year, edition, pages
Amsterdam: John Benjamins Publishing Company, 2014. 13-38 p.
, Studies in Language Companion Series, ISSN 0165-7763 ; 150
National Category
Languages and Literature
URN: urn:nbn:se:su:diva-109336DOI: 10.1075/slcs.150.02mayISBN: 978-90-272-5915-8ISBN: 978-90-272-7064-1OAI: diva2:764225
Available from: 2014-11-18 Created: 2014-11-18 Last updated: 2014-12-09Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Wälchli, Bernhard
By organisation
General Linguistics
Languages and Literature

Search outside of DiVA

GoogleGoogle Scholar
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

Altmetric score

Total: 32 hits
ReferencesLink to record
Permanent link

Direct link