Distribution kernels based on moments of counts

Corinna Cortes, Mehryar Mohri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many applications in text and speech processing require the analysis of distributions of variable-length sequences. We recently introduced a general kernel framework, rational kernels, to extend kernel methods to the analysis of such variable-length sequences or more generally weighted automata. These kernels are efficient to compute and have been successfully used in applications such as spoken-dialog classification using Support Vector Machines. However, the rational kernels previously introduced do not fully encompass distributions over alternate sequences. Prior similarity measures between two weighted automata are based only on the expected counts of cooccurring subsequences and ignore similarities (or dissimilarities) in higher order moments of the distributions of these counts. In this paper, we introduce a new family of rational kernels, moment kernels, that precisely exploit this additional information. These kernels are distribution kernels based on moments of counts of strings. We describe efficient algorithms to compute moment kernels and apply them to several difficult spoken-dialog classification tasks. Our experiments show that using the second moment of the counts of n-gram sequences consistently improves the classification accuracy in these tasks.

Original languageEnglish (US)
Title of host publicationProceedings, Twenty-First International Conference on Machine Learning, ICML 2004
EditorsR. Greiner, D. Schuurmans
Pages193-200
Number of pages8
StatePublished - 2004
EventProceedings, Twenty-First International Conference on Machine Learning, ICML 2004 - Banff, Alta, Canada
Duration: Jul 4 2004Jul 8 2004

Publication series

NameProceedings, Twenty-First International Conference on Machine Learning, ICML 2004

Other

OtherProceedings, Twenty-First International Conference on Machine Learning, ICML 2004
Country/TerritoryCanada
CityBanff, Alta
Period7/4/047/8/04

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Distribution kernels based on moments of counts'. Together they form a unique fingerprint.

Cite this