Unsupervised word categorization using self-organizing maps and automatically extracted morphs

Authors:
Mikaela Klami;Krista Lagus
Affiliations:
Adaptive Informatics Research Centre, Helsinki University of Technology, TKK, Finland;Adaptive Informatics Research Centre, Helsinki University of Technology, TKK, Finland
Venue:
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Year:
2006

Citing 7
Cited 0

Self-Organizing Maps

Self-Organizing Maps
Unsupervised learning of the morphology of a natural language

Computational Linguistics
Automatic word sense discrimination

Computational Linguistics - Special issue on word sense disambiguation
Distributional clustering of English words

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Morphological cues for lexical semantics

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Clustering verbs semantically according to their alternation behaviour

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Unsupervised discovery of morphemes

MPL '02 Proceedings of the ACL-02 workshop on Morphological and phonological learning - Volume 6

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic creation of syntactic and semantic word categorizations is a challenging problem for highly inflecting languages due to excessive data sparsity. Moreover, the study of colloquial language resources requires the utilization of fully corpus-based tools. We present a completely automated approach for producing word categorizations for morphologically rich languages. Self-Organizing Map (SOM) is utilized for clustering words based on the morphological properties of the context words. These properties are extracted using an automated morphological segmentation algorithm called Morfessor. Our experiments on a colloquial Finnish corpus of stories told by young children show that utilizing unsupervised morphs as features leads to clearly improved clusterings when compared to the use of whole context words as features.