Change search
ReferencesLink to record
Permanent link

Direct link
Cross-lingual comparison between distributionally determined word similarity networks
RISE, Swedish ICT, SICS. Userware.
RISE, Swedish ICT, SICS. Userware.ORCID iD: 0000-0003-4042-4919
Number of Authors: 2
2010 (English)Conference paper (Refereed)
Abstract [en]

As an initial effort to identify universal and language-specific factors that influence the behavior of distributional models, we have formulated a distributionally determined word similarity network model, implemented it for eleven different languages, and compared the resulting networks. In the model, vertices constitute words and two words are linked if they occur in similar contexts. The model is found to capture clear isomorphisms across languages in terms of syntactic and semantic classes, as well as functional categories of abstract discourse markers. Language specific morphology is found to be a dominating factor for the accuracy of the model.

Place, publisher, year, edition, pages
2010, 10.
National Category
Computer and Information Science
URN: urn:nbn:se:ri:diva-22693OAI: diva2:1042258
TextGraphs-5, ACL Workshop on Graph-based Methods for Natural Language Processing, July 2010, Uppsala, Sweden
Swedish Research Council
Available from: 2016-10-31 Created: 2016-10-31 Last updated: 2016-12-28

Open Access in DiVA

fulltext(167 kB)2 downloads
File information
File name FULLTEXT01.pdfFile size 167 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Karlgren, Jussi
By organisation
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 2 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: 6 hits
ReferencesLink to record
Permanent link

Direct link