Change search
ReferencesLink to record
Permanent link

Direct link
Global Evaluation of Random Indexing through Swedish Word Clustering Compared to the People’s Dictionary of Synonyms
KTH, School of Computer Science and Communication (CSC), Theoretical Computer Science, TCS.
KTH, School of Computer Science and Communication (CSC), Theoretical Computer Science, TCS.ORCID iD: 0000-0003-3199-8953
2010 (English)Conference paper (Refereed)
Abstract [en]

Evaluation of word space models is usually local in the sense that it only considers words that are deemed very similar by the model. We propose a global evaluation scheme based on clustering of the words. A clustering of high quality in an external evaluation against a semantic resource, such as a dictionary of synonyms, indicates a word space model of high quality. We use Random Indexing to create several different models and compare them by clustering evaluation against the People’s Dictionary of Synonyms, a list of Swedish synonyms that are graded by the public. Most notably we get better results for models based on syntagmatic information (words that appear together) than for models based on paradigmatic information (words that appear in similar contexts). This is quite contrary to previous results that have been presented for local evaluation. Clusterings to ten clusters result in a recall of 83 % for a syntagmatic model, compared to 34% for a comparable paradigmatic model, and 10% for a random partition.

Place, publisher, year, edition, pages
National Category
Computer Science
URN: urn:nbn:se:kth:diva-81051OAI: diva2:497041
Third Swedish Language Technology Conference, SLTC-2010. Linköping, Sweden. October 28-29 2010
QC 20120424Available from: 2012-02-10 Created: 2012-02-10 Last updated: 2012-04-24Bibliographically approved

Open Access in DiVA

No full text

Other links

Search in DiVA

By author/editor
Rosell, MagnusKann, Viggo
By organisation
Theoretical Computer Science, TCS
Computer Science

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

Total: 24 hits
ReferencesLink to record
Permanent link

Direct link