String Distance-Based Stemming of the Highly Inflected Croatian Language
Jan Šnajder, Bojana Dalbelo Bašić · Recent Advances in Natural Language Processing · 2009
Stemming refers to the grouping of morphologically related words into so-called stem classes for the purpose of improving information retrieval performance. Traditional approaches to stemming are language-specific and require a substantial amount of linguistic knowledge. A viable alternative is string distance-based stemming, in which stem classes are obtained by clustering word-forms from a corpus. In this paper, we apply string distance-based stemming to the highly inflected Croatian language using a number of string distance measures proposed in the literature. We focus on evaluating the stemming performance at both inflectional and derivational level, and investigate how this performance relates to the choice of the distance threshold value. Although our focus is on the Croatian language, we believe our results transfer well to languages of similar morphological complexity.