This dissertation studies information extraction (IE), the problem of extracting structured information from unstructured data. Example IE tasks include extracting person names from news articles, product information from e-commerce Web pages, street addresses from emails, and names of emerging music bands from blogs. IE is all increasingly…

The progress made on 65 contracts and grants active during 1968 in the four areas designated by the COSATI subject headings: (1) documentation and information technology, (2) language and linguistics, (3) bionics and (4) information theory are presented. Selected highlights of the program are given in the introductory chapter. This is followed by…

The twenty-second in a series, this report describes research in information organization and retrieval conducted by the Department of Computer Science at Cornell University. The report covers work carried out during the period summer 1972 through summer 1974 and is divided into four parts: indexing theory, automatic content analysis, feedback…