Presentation 2008/7/10
Rich Annotation : Knowledge Extraction focusing on Named Entities
Genichiro KIKUI, Yoshihiro MATSUO, Nozomi KOBAYASHI, Toru HIRANO, Hisako ASANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a general purpose information extraction system. The system has two main functions. The first function associates a named entity (NE) expression with its "referent", which is defined in external databases such as Wikipedia and a geographic database. The second function extracts semantically related pairs of NEs. The system can find an NE pair across sentence boundaries by using a machine learning method that refers to contextual information. The paper also presents an example of extracted information in a structuralized format.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) named entity / information extraction / web text mining
Paper # NLC2008-13
Date of Issue

Conference Information
Committee NLC
Conference Date 2008/7/10(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) Rich Annotation : Knowledge Extraction focusing on Named Entities
Sub Title (in English)
Keyword(1) named entity
Keyword(2) information extraction
Keyword(3) web text mining
1st Author's Name Genichiro KIKUI
1st Author's Affiliation NTT Cyber Space Laboratories()
2nd Author's Name Yoshihiro MATSUO
2nd Author's Affiliation NTT Cyber Space Laboratories
3rd Author's Name Nozomi KOBAYASHI
3rd Author's Affiliation NTT Cyber Space Laboratories
4th Author's Name Toru HIRANO
4th Author's Affiliation NTT Cyber Space Laboratories
5th Author's Name Hisako ASANO
5th Author's Affiliation NTT Cyber Space Laboratories
Date 2008/7/10
Paper # NLC2008-13
Volume (vol) vol.108
Number (no) 141
Page pp.pp.-
#Pages 6
Date of Issue