Paper: Towards Robust Animacy Classification Using Morphosyntactic Distributional Features

ACL ID E06-3008
Title Towards Robust Animacy Classification Using Morphosyntactic Distributional Features
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

This paper presents results from ex- periments in automatic classification of animacy for Norwegian nouns using decision-tree classifiers. The method makes use of relative frequency measures for linguistically motivated morphosyn- tactic features extracted from an automati- cally annotated corpus of Norwegian. The classifiers are evaluated using leave-one- out training and testing and the initial re- sults are promising (approaching 90% ac- curacy)forhighfrequency nouns, however deteriorate gradually as lower frequency nouns are classified. Experiments at- tempting to empirically locate a frequency threshold for the classification method in- dicate that a subset of the chosen mor- phosyntactic features exhibit a notable re- silience to data sparseness. Results will be presented which show ...