Bibliographic File Integration System Using PYAT Identifiers
Sachiko Matsui, Yoshiro Matsuda, Chooichiro Asano, 幸子 松井, 芳郎 松田, 長一郎 浅野 · QIR (Kyushu University Institutional Repository) (Kyushu University) · 1990
Identification of duplicate items in different bibliographic databases is one of the most important operations to construct large-scale databases for practical use. The PYAT identifiers are general terms for the techniques we developed for effective identification. P, Y, A, T are the components of the identifiers, such as publishing place, year, author name and title. The identification experiment clarified that components of identifiers give different effects on the identification efficiency: the success ratio in identifying duplicates by computer. Therefore, the identification efficiency thus acquired can be evaluated as useful data for composing a more effective identifier.