Presentation 2001/7/9
Learning to Combine Outputs of Multiple Japanese Named Entity Extractors
Takehito Utsuro, Manabu Sassano, Kiyotaka Uchimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a methodfor learning a classifier which combines outputs of more than one Japanese named entity extractors. Individual models to be combined are based on maximum entropy models, one of which always considers surrounding contexts of a fixed length, while the other considers those of variable lengths according to the number of constituent morphemes of named entities. Experimental evaluation shows that the proposed method achieves improvement over the best known results with named entity extractors based on maximum entropy models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Japanese named entity extraction / system combination / stacking / variable context length / maximum entropy model / decision list learning
Paper # NLC2001-13
Date of Issue

Conference Information
Committee NLC
Conference Date 2001/7/9(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning to Combine Outputs of Multiple Japanese Named Entity Extractors
Sub Title (in English)
Keyword(1) Japanese named entity extraction
Keyword(2) system combination
Keyword(3) stacking
Keyword(4) variable context length
Keyword(5) maximum entropy model
Keyword(6) decision list learning
1st Author's Name Takehito Utsuro
1st Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Manabu Sassano
2nd Author's Affiliation Fujitsu Laboratories, Ltd.
3rd Author's Name Kiyotaka Uchimoto
3rd Author's Affiliation Communications Research Laboratory
Date 2001/7/9
Paper # NLC2001-13
Volume (vol) vol.101
Number (no) 189
Page pp.pp.-
#Pages 8
Date of Issue