IEICE TRANSACTIONS on Information
Robust Toponym Resolution Based on Surface Statistics
Summary :
Toponyms and other named entities are main issues in unknown word processing problem. Our purpose is to salvage unknown toponyms, not only for avoiding noises but also providing them information of area candidates to where they may belong. Most of previous toponym resolution methods were targeting disambiguation among area candidates, which is caused by the multiple existence of a toponym. These approaches were mostly based on gazetteers and contexts. When it comes to the documents which may contain toponyms worldwide, like newspaper articles, toponym resolution is not just an ambiguity resolution, but an area candidate selection from all the areas on Earth. Thus we propose an automatic toponym resolution method which enables to identify its area candidates based only on their surface statistics, in place of dictionary-lookup approaches. Our method combines two modules, area candidate reduction and area candidate examination which uses block-unit data, to obtain high accuracy without reducing recall rate. Our empirical result showed 85.54% precision rate, 91.92% recall rate and .89 F-measure value on average. This method is a flexible and robust approach for toponym resolution targeting unrestricted number of areas.
- Publication
- IEICE TRANSACTIONS on Information Vol.E92-D No.12 pp.2313-2320
- Publication Date
- 2009/12/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E92.D.2313
- Type of Manuscript
- Special Section PAPER (Special Section on Natural Language Processing and its Applications)
- Category
- Unknown Word Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tomohisa SANO, Shiho Hoshi NOBESAWA, Hiroyuki OKAMOTO, Hiroya SUSUKI, Masaki MATSUBARA, Hiroaki SAITO, "Robust Toponym Resolution Based on Surface Statistics" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 12, pp. 2313-2320, December 2009, doi: 10.1587/transinf.E92.D.2313.
Abstract: Toponyms and other named entities are main issues in unknown word processing problem. Our purpose is to salvage unknown toponyms, not only for avoiding noises but also providing them information of area candidates to where they may belong. Most of previous toponym resolution methods were targeting disambiguation among area candidates, which is caused by the multiple existence of a toponym. These approaches were mostly based on gazetteers and contexts. When it comes to the documents which may contain toponyms worldwide, like newspaper articles, toponym resolution is not just an ambiguity resolution, but an area candidate selection from all the areas on Earth. Thus we propose an automatic toponym resolution method which enables to identify its area candidates based only on their surface statistics, in place of dictionary-lookup approaches. Our method combines two modules, area candidate reduction and area candidate examination which uses block-unit data, to obtain high accuracy without reducing recall rate. Our empirical result showed 85.54% precision rate, 91.92% recall rate and .89 F-measure value on average. This method is a flexible and robust approach for toponym resolution targeting unrestricted number of areas.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2313/_p
Copy
@ARTICLE{e92-d_12_2313,
author={Tomohisa SANO, Shiho Hoshi NOBESAWA, Hiroyuki OKAMOTO, Hiroya SUSUKI, Masaki MATSUBARA, Hiroaki SAITO, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Toponym Resolution Based on Surface Statistics},
year={2009},
volume={E92-D},
number={12},
pages={2313-2320},
abstract={Toponyms and other named entities are main issues in unknown word processing problem. Our purpose is to salvage unknown toponyms, not only for avoiding noises but also providing them information of area candidates to where they may belong. Most of previous toponym resolution methods were targeting disambiguation among area candidates, which is caused by the multiple existence of a toponym. These approaches were mostly based on gazetteers and contexts. When it comes to the documents which may contain toponyms worldwide, like newspaper articles, toponym resolution is not just an ambiguity resolution, but an area candidate selection from all the areas on Earth. Thus we propose an automatic toponym resolution method which enables to identify its area candidates based only on their surface statistics, in place of dictionary-lookup approaches. Our method combines two modules, area candidate reduction and area candidate examination which uses block-unit data, to obtain high accuracy without reducing recall rate. Our empirical result showed 85.54% precision rate, 91.92% recall rate and .89 F-measure value on average. This method is a flexible and robust approach for toponym resolution targeting unrestricted number of areas.},
keywords={},
doi={10.1587/transinf.E92.D.2313},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Robust Toponym Resolution Based on Surface Statistics
T2 - IEICE TRANSACTIONS on Information
SP - 2313
EP - 2320
AU - Tomohisa SANO
AU - Shiho Hoshi NOBESAWA
AU - Hiroyuki OKAMOTO
AU - Hiroya SUSUKI
AU - Masaki MATSUBARA
AU - Hiroaki SAITO
PY - 2009
DO - 10.1587/transinf.E92.D.2313
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2009
AB - Toponyms and other named entities are main issues in unknown word processing problem. Our purpose is to salvage unknown toponyms, not only for avoiding noises but also providing them information of area candidates to where they may belong. Most of previous toponym resolution methods were targeting disambiguation among area candidates, which is caused by the multiple existence of a toponym. These approaches were mostly based on gazetteers and contexts. When it comes to the documents which may contain toponyms worldwide, like newspaper articles, toponym resolution is not just an ambiguity resolution, but an area candidate selection from all the areas on Earth. Thus we propose an automatic toponym resolution method which enables to identify its area candidates based only on their surface statistics, in place of dictionary-lookup approaches. Our method combines two modules, area candidate reduction and area candidate examination which uses block-unit data, to obtain high accuracy without reducing recall rate. Our empirical result showed 85.54% precision rate, 91.92% recall rate and .89 F-measure value on average. This method is a flexible and robust approach for toponym resolution targeting unrestricted number of areas.
ER -
English
