Daftar Abstrak Tesis Program S2
Fakultas Ilmu Komputer Universitas Indonesia - Tahun 2002

Noviari Sugianto Pengembangan sistem ekstraksi informasi berbahasa Indonesia An enourmous amount of information exists only in a natural language form. If this information is to be automatically manipulated and analyzed, it must first be distilled into a more structured form. Information extraction refers to the problem of finding useful information in a collection of texts, and encoding that information in a format suitable for incorporation into a database. Until now, there is little interest in developing information in a format suitable for incorporation into a database. Until now, there is little interest in developing information extraction systems for Indonesian language. Information extraction system for Indonesian language offer hte potensial of analyzing information from a collection of Indonesian texts. Therefore, this research builds an information extraction system for Indonesian language. This information extraction system is called SEIBI (Sistem Ekstraksi Informasi Berbahasa Indonesia - information extraction system for Indonesian language). SEIBI is built based on CIRCUS [LEHN93]. The scope of this research was limited to build information extraction system that extracts the goal, the scope of the work, and the conclusion from the collections of Undergraduate thesis's abstracts at Faculty of COmputer Science University of Indonesia. SEIBI was able to extracts 56 goal...