Automatic extraction of citations from the text of English-language patents - an example of template mining

Abstract

Methods for automatically isolating and extracting biblio graphic references from the full texts of patents are described and evaluated; these include citations both to patents and to other bibliographic sources. Patents are unusual as citing documents in that citations occur princi pally in the text of the abstracts or description parts of the documents, rather than as footnotes or in separate sections. A template mining approach has been developed for this purpose, to relieve patent examiners of the chore of doing this manually.