Markov models for clusters in concordance compression

Abraham Bookstein, S. Klein, Timo Raita

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

An earlier paper developed a procedure for compressing concordances, assuming that all elements occurred independently. In this paper, the earlier models are extended to take the possibility of clustering into account. The authors suggest several models adapted to concordances of large full-text information retrieval systems, which are generally subject to clustering.
Original languageAmerican English
Title of host publicationData Compression Conference, 1994. DCC'94. Proceedings
PublisherIEEE
StatePublished - 1994

Bibliographical note

Place of conference:USA

Fingerprint

Dive into the research topics of 'Markov models for clusters in concordance compression'. Together they form a unique fingerprint.

Cite this