Ephemeral Document Clustering for Web Applications

Ephemeral Document Clustering for Web Applications (2000)

Cached

Download Links

by Yoelle S. Maarek , Ronald Fagin , Israel Z. Ben-Shaul , Dan Pelleg

Venue:	IBM RESEARCH REPORT RJ 10186
Citations:	16 - 0 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Ephemeral document clustering for web applications	INFERENCE
AUTHOR NAME	Yoelle S. Maarek	SVM HeaderParse 0.2
AUTHOR AFFIL	, Israel Z. Ben-Shaul z	SVM HeaderParse 0.2
AUTHOR NAME	Ronaldfagin Y	SVM HeaderParse 0.2
AUTHOR AFFIL	, Israel Z. Ben-Shaul z	SVM HeaderParse 0.2
AUTHOR NAME	Dan Pelleg X	SVM HeaderParse 0.2
AUTHOR AFFIL	; IBM Research Report RJ 10186, April 2000.; y IBM Almaden Research Center; z Department of Electrical Engineering; x Department of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, USA.; 1	SVM HeaderParse 0.2
AUTHOR ADDR	; IBM Research in Haifa, MATAM, Haifa 31905, ISRAEL.; 650 Harry Road, San Jose, California, USA. Email: fagin@almaden.ibm.com; Technion, Israel Institute of Technology, Haifa 32000, ISRAEL. Email:	SVM HeaderParse 0.2
ABSTRACT	We revisit document clustering in the context of the Web. Speci cally, weinvestigate on-line ephemeral clustering, whereby the input document set is generated dynamically, typically by search results, and the output clustering hierarchy has a short life span, and is used for interactive browsing purposes. Ephemeral clustering for interactive use introduces several new challenges. It requires an e cient algorithm, since clustering is performed on-line. It also requires high precision, because users who are not domain experts are less tolerant to errors, and because the resulting hierarchy isfully automatically generated, as opposed to o-line clustering in which the hierarchy is often manually modi ed. Finally, interactive clustering requires a presentation layer that enables users to e ectively browse the hierarchy, including visualization techniques and automatic annotations of the hierarchy. We present new concepts, techniques and algorithms that tailor clustering to these requirements. More speci cally, we improve precision by feeding the clustering algorithm with more precise pro les using \lexical a nities " as indexing units. We give an optimal complete-link Hierarchical Agglomerative Clustering algorithm, with O(n 2) time complexity. Finally, weprovide a visual yet light Java-based implementation of the presentation layer. We demonstrate the utility of ephemeral clustering through a search assistance utility thatembodies these ideas.	SVM HeaderParse 0.2
YEAR	2000	INFERENCE
VENUE	IBM Research Report RJ 10186	INFERENCE
VENUE TYPE	TECHREPORT	INFERENCE
TECH	Technical Report RJ 10186, IBM Research	INFERENCE
CITATIONS	35 found	ParsCit 1.0