Iterative Residual Rescaling: An Analysis and Generalization of LSI

Simple item page
dc.creatorAndo, Rie Kubota
dc.creatorLee, Lillian
dc.date2001-06-17
dc.date.accessioned2026-07-07T03:17:16Z
dc.date.available2026-07-07T03:17:16Z
dc.descriptionWe consider the problem of creating document representations in which inter-document similarity measurements correspond to semantic similarity. We first present a novel subspace-based framework for formalizing this task. Using this framework, we derive a new analysis of Latent Semantic Indexing (LSI), showing a precise relationship between its performance and the uniformity of the underlying distribution of documents over topics. This analysis helps explain the improvements gained by Ando's (2000) Iterative Residual Rescaling (IRR) algorithm: IRR can compensate for distributional non-uniformity. A further benefit of our framework is that it provides a well-motivated, effective method for automatically determining the rescaling factor IRR depends on, leading to further improvements. A series of experiments over various settings and with several evaluation metrics validates our claims.
dc.descriptionTo appear in the proceedings of SIGIR 2001. 11 pages
dc.identifierhttps://arxiv.org/abs/cs/0106039
dc.identifierhttp://arxiv.org/abs/cs/0106039
dc.identifierProceedings of the 24th SIGIR, pp. 154--162, 2001.
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30657
dc.subjectComputation and Language
dc.subjectInformation Retrieval
dc.subjectH.3.3; I.2.7
dc.titleIterative Residual Rescaling: An Analysis and Generalization of LSI
dc.typetext

Files

Collections

arXiv