Presentation 2014-06-15
Detection of Community Events Using HTML Structure of Web Documents
Kazuki ASANO, Koichi TAKEUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently many community events are held in local areas. To join the events must be enjoyable, however, these community events are local information then it is difficult to capture the events if we do not know the existence. Then the aim of this research is to collect the information of the local community events that may not be announced previously in newspapers nor TV, but previously announced by the Web sites. In this manuscript, we report preliminary results of applying two methods: (1) a rule-based based on HTML structure and character pattern, and (2) a support vectore machine based system utilizing features used in the method (1). The experimental results show that the SVM-based system can extract name of events, dates, period of time and places in 59.4% accruacy. We will discuss how we can improve the current system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) event extraction / Support Vector Machine / html structure analysis
Paper # NLC2014-10
Date of Issue

Conference Information
Committee NLC
Conference Date 2014/6/7(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) Detection of Community Events Using HTML Structure of Web Documents
Sub Title (in English)
Keyword(1) event extraction
Keyword(2) Support Vector Machine
Keyword(3) html structure analysis
1st Author's Name Kazuki ASANO
1st Author's Affiliation Graduate School of Natural Sience and Technology, Okayama University()
2nd Author's Name Koichi TAKEUCHI
2nd Author's Affiliation Graduate School of Natural Sience and Technology, Okayama University
Date 2014-06-15
Paper # NLC2014-10
Volume (vol) vol.114
Number (no) 81
Page pp.pp.-
#Pages 6
Date of Issue