Extending and Updating the Finnish Wordnet

This paper presents simple methods for adding new words to a wordnet. We use the Finnish wordnet, FinnWordNet, as an example. We pay particular attention to high- and medium-frequency words thus far missing from FinnWordNet, and arrive at an estimate for the number of culture-specific words among them. We also find that the majority of the high- and medium-frequency words are compounds, which makes them relatively easy to add by using the head word of a compound to locate hypernym synset candidates. Another goal of ours is to add new synonyms to the existing synsets of FinnWordNet. We present a method that finds candidates for new synonyms from a bilingual lexical resource by exploiting the direct word sense translation correspondences between FinnWordNet and the Princeton WordNet. We apply the method to the interlanguage links between articles on the same topic in the Finnish and English Wikipedias on the one hand, and to the translations in the Finnish and English Wiktionaries on the other, and compare the results.