Creating the Open Wordnet Bahasa
Nurril Hirfana Bte Mohamed Noor, Suerya Sapuan, Francis T. Bond · Institutional Repositories DataBase (IRDB) · 2011
This paper outlines the creation of the Wordnet Bahasa as a resource for the study of lexical semantics in the Malay language.It is created by combining information from several lexical resources: the French-English-Malay dictionary FEM, the KAmus Melayu-Inggeris KAMI, and wordnets for English, French and Chinese.Construction went through three steps: (i) automatic building of word candidates; (ii) evaluation and selection of acceptable candidates from merging of lexicons; (iii) final hand check of the 5,000 core synsets.Our Wordnet Bahasa is only in the first phase of building a full fledged wordNet and needs to be further expanded, however it is already large enough to be useful for sense tagging both Malay and Indonesian.