Publication details

Enhancing WordNets with Morphological Relations: A Case Study from Czech, English and Zulu


BOSCH Sonja FELLBAUM Christiane PALA Karel

Year of publication 2008
Type Article in Proceedings
Conference Proceedings of the Fourth Global WordNet Conference
MU Faculty or unit

Faculty of Informatics

Web Conference web
Field Informatics
Keywords WordNet; morphological relations
Description WordNets are most useful when their network is dense, i.e., when a given word of synsets is connected to many other words and synsets with lexical and conceptual relations. More links mean more semantic information and thus better discrimination of individual word senses. In the paper we discuss one kind of cross-POS relation for English, Czech and Bantu WordNets. Many languages have rules whereby new words are derived regularly and productively from existing words via morphological processes. The morphologically unmarked base words and the derived words, which share a semantic core with the base words, can be interlinked and integrated into WordNets, where they typically form "derivational nests", or subnets. We describe efforts to capture the morphological and semantic regularities of derivational processes in English, Czech and Bantu to compare the linguistic mechanisms and to exploit them for suitable computational processing and WordNet construction.
Related projects: