The impact of phrases in document clustering for Swedish
Magnus Rosell, Sumithra Velupillai · DSpace repository (University of Tartu) · 2005
We have investigated the impact of using phrases in the vector space model for clustering documents in Swedish in different ways.The investigation is carried out on two text sets from different domains: one set of newspaper articles and one set of medical papers.The use of phrases do not improve results relative the ordinary use of words.The results differ significantly between the text types.This indicates that one could benefit from different text representations for different domains although a fundamentally different approach probably would be needed.