Query Log Driven Web Search Results Clustering - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Query Log Driven Web Search Results Clustering

Abstract

recently shown increasing performances motivated by the use of external resources. Following this trend, we present a new algo- rithm called Dual C-Means, which provides a theoretical back- ground for clustering in different representation spaces. Its origi- nality relies on the fact that external resources can drive the cluster- ing process as well as the labeling task in a single step. To validate our hypotheses, a series of experiments are conducted over differ- ent standard datasets and in particular over a new dataset built from the TREC Web Track 2012 to take into account query logs infor- mation. The comprehensive empirical evaluation of the proposed approach demonstrates its significant advantages over traditional clustering and labeling techniques.
Fichier principal
Vignette du fichier
ACTI-MORENO-2014-2.pdf (339.97 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01070306 , version 1 (01-10-2014)

Identifiers

  • HAL Id : hal-01070306 , version 1

Cite

José G. Moreno, Gaël Dias, Guillaume Cleuziou. Query Log Driven Web Search Results Clustering. 37th Annual ACM SIGIR Conference (SIGIR 2014), Jul 2014, Gold Coast, Australia. 10p. ⟨hal-01070306⟩
103 View
333 Download

Share

Gmail Facebook X LinkedIn More