Text Assisted Defence Information Extractor
Nishant Kumar, Shikha Suman, Anubhuti Khera, Kanika Agarwal · 2013
A gazetteer is a directory which consists of information about places, people etc. The role of the gazetteer is to identify entity names in the text based on lists. For example, ANNIE gazetteer lists, used in GATE, are plain text files, with one entry per line. Gazetteer list is a file with a ‗.lst‘ extension that consists of one entry at each line. A gazetteer list typically includes named entities (names, institutions, etc.), entity components such as prefixes of locations etc. Each list has a major type, minor type and a language. It is preferable to specify the major type while creating the list, while specifying the minor type and language is optional. We can modify the gazetteer lists and even create new ones. The major and minor types and the entries in the lists can also be modified. The newly created list needs to be mentioned with its major and minor type in the ‗.def‘ file of the ANNIE‘s gazetteer. The transducer basically uses up the entries in the gazetteer to create new annotations.