engleski

Disambiguation of Homographic Adjective and Adverb Forms in Croatian Texts

We propose a NooJ morphosyntactic tagging postprocessing module for resolving problems which arise in disambiguation of adjectives and adverbs that, due to morphology of the Croatian language, appear in the same form. Specifically, forms of descriptive adjectives in the nominative singular case in the neuter gender are the same as the forms of the adverbs that are made from those adjectives by suffixation. We have implemented a set of local grammars for correcting such occurences and applied it on two corpora of Croatian texts and manually evaluated the module. We suggest the inclusion of such a model of disambiguation to existing pipelines of processing Croatian text and developing Croatian language resources in order to improve the efficiency and accuracy of those tools and procedures.

disambiguation, adjectives, adverbs, homography, Croatian language

nije evidentirano