Extended Named Entity Hierarchy
Satoshi Sekine (New York University 715 Broadway, 7th floor, New York, NY 10003, USA)
Kiyoshi Sudo (New York University 715 Broadway, 7th floor, New York, NY 10003, USA)
Chikashi Nobata (Communications Research Laboratory 2-2-2 Hikaridai Seika-cho, Soraku-gun Kyoto 619-0289 Japan)
WP5: Components & Systems
The tagging of Named Entities (NE), the names of particular things or classes and numeric expressions, is regarded as an important component technology for many NLP applications. These applications include Information Extraction, from which it was born, Question-Answering, Summarization and Information Retrieval. However, up to now, the number of NE types has been quite limited, 7 in MUC, 8 in IREX and 5 in the ACE program. Many more kinds of things have proper names or proper classes of expressions, and also finer distinctions are needed for some applications. We now propose a Named Entity hierarchy which contains about 150 NE types. The focus of this paper is the design of the hierarchy and we would like to provide this resource for any application. We report the design and development procedure of the hierarchy.