Presentation 2004-06-21
Kernel-based Discriminative Learning Algorithms for Labeling Structured Data
Hisashi KASHIMA, Yuta TSUBOI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We introduce a new perceptron-based discriminative learning algorithm for labeling structural data such as sequences, trees and graphs. Since it is fully kernelized and employs the pointwise label prediction, large features including arbitrary number of hidden variables can be incorporated with polynomial time complexity. This is contrasted with existing labelers that can handle only features of a small number of hidden variables such as Maximum Entropy Markov Models and Conditional Random Fields. We also introduce several kernel functions for labeling sequences, trees and graphs and the efficient algorithms for them.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kernel Methods / Perceptron / Marginalized Kernel / Named Entity Recognition / Information Extraction
Paper # AI2004-3
Date of Issue

Conference Information
Committee AI
Conference Date 2004/6/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Kernel-based Discriminative Learning Algorithms for Labeling Structured Data
Sub Title (in English)
Keyword(1) Kernel Methods
Keyword(2) Perceptron
Keyword(3) Marginalized Kernel
Keyword(4) Named Entity Recognition
Keyword(5) Information Extraction
1st Author's Name Hisashi KASHIMA
1st Author's Affiliation IBM Tokyo Research Laboratory()
2nd Author's Name Yuta TSUBOI
2nd Author's Affiliation IBM Tokyo Research Laboratory
Date 2004-06-21
Paper # AI2004-3
Volume (vol) vol.104
Number (no) 133
Page pp.pp.-
#Pages 6
Date of Issue