メタデータ付与のための住所録自動生成  [in Japanese] Automatic Generation of an Address Book for Metadata Annotation  [in Japanese]

Access this Article

Search this Article

Author(s)

    • 村山 紀文 MURAYAMA Norifumi
    • 東京工業大学大学院 総合理工学研究科 Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
    • 南野 朋之 NANNO Tomoyuki
    • 東京工業大学大学院 総合理工学研究科 Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
    • 奥村 学 OKUMURA Manabu
    • 東京工業大学 精密工学研究所 Precision and Intelligence Laboratory, Tokyo Institute of Technology

Abstract

位置情報はWeb上の情報の組織化において有用な情報と考えられるが,現状では,陽に位置情報が明記されていないため,位置情報を利用できない場合が多い.しかし,店名などの固有名はそれ自体は位置情報を直接的に示すものではないが,位置情報と関連した固有名と考えることができる. これらの固有名に対し,位置情報をメタデータとして付与することが出来れば,その位置情報を利用することが出来る. 本研究では,そのようなメタデータ付与のために必要な,固有名と対応する位置情報のデータベースを,Web上の文書から自動的に作成する手法を示す. 本稿では特に,その最初のステップとして,固有名・住所・電話番号の三つ組をWeb上の文書から自動的に抽出する手法を示す.Location information in web pages is very useful to organize information in them. However, many web pages do not include apparent location information in themselves. Though named entities, such as names of stores, are not location information, we think those named entities are related to location information. If we can annotate location information to such named entities, we can use these pages with location information. Therefore, our goal is to extract meta data base for such named entities, that include their location information, telephone number and other information. In this paper, we present a method to automatically constract triples (named entity, its telephone number, its address) from the WWW as a first step of meta data base construction.

Location information in web pages is very useful to organize information in them. However, many web pages do not include apparent location information in themselves. Though named entities, such as names of stores, are not location information, we think those named entities are related to location information. If we can annotate location information to such named entities, we can use these pages with location information. Therefore, our goal is to extract meta data base for such named entities, that include their location information, telephone number and other information. In this paper, we present a method to automatically constract triples (named entity, its telephone number, its address) from the WWW as a first step of meta data base construction.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 2004(73(2004-NL-162)), 41-47, 2004-07-15

    Information Processing Society of Japan (IPSJ)

References:  9

Cited by:  2

Codes

  • NII Article ID (NAID)
    110002911726
  • NII NACSIS-CAT ID (NCID)
    AN10115061
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09196072
  • NDL Article ID
    7064572
  • NDL Source Classification
    ZM13(科学技術--科学技術一般--データ処理・計算機)
  • NDL Call No.
    Z14-1121
  • Data Source
    CJP  CJPref  NDL  NII-ELS  IPSJ 
Page Top