@inproceedings{nakatani-etal-2026-large,
title = "A Large-Scale Dataset for Linking-Based Geocoding",
author = "Nakatani, Hibiki and
Yasui, Yuichiro and
Wakamoto, Ryosuke and
Ishii, Masayuki and
Suizu, Tetsuhisa and
Ouchi, Hiroki and
Watanabe, Taro",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.606/",
doi = "10.63317/2pv6oidqzqs9",
pages = "7644--7654",
abstract = "Linking-based geocoding is the task of linking location mentions in text to their corresponding entries in a geographic database (Geo-DB) and assigning precise coordinates. Although the task and its technology are essential for spatial information extraction, existing datasets are manually curated and lack sufficient data for training accurate models. To address this limitation, we automatically construct a large-scale dataset for linking-based geocoding by leveraging publicly available resources to generate data efficiently at scale. Specifically, we align location mentions in the first paragraphs of Japanese Wikipedia articles with their associated Wikidata entries containing geographic attributes. Wikipedia provides natural textual contexts, while Wikidata offers structured data such as coordinates, place types, and administrative divisions, which can serve as rich metadata for future extensions. Our experiments show that models trained on our dataset achieve strong performance not only on in-domain data, i.e., Wikipedia, but also on out-of-domain newspaper articles, and further confirm that hard negative mining substantially improves disambiguation among confusable candidates. Although the dataset focuses on Japanese, the construction method is language-agnostic and can be extended to other languages with sufficient Wikipedia and Wikidata coverage."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakatani-etal-2026-large">
<titleInfo>
<title>A Large-Scale Dataset for Linking-Based Geocoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hibiki</namePart>
<namePart type="family">Nakatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuichiro</namePart>
<namePart type="family">Yasui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryosuke</namePart>
<namePart type="family">Wakamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masayuki</namePart>
<namePart type="family">Ishii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuhisa</namePart>
<namePart type="family">Suizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Linking-based geocoding is the task of linking location mentions in text to their corresponding entries in a geographic database (Geo-DB) and assigning precise coordinates. Although the task and its technology are essential for spatial information extraction, existing datasets are manually curated and lack sufficient data for training accurate models. To address this limitation, we automatically construct a large-scale dataset for linking-based geocoding by leveraging publicly available resources to generate data efficiently at scale. Specifically, we align location mentions in the first paragraphs of Japanese Wikipedia articles with their associated Wikidata entries containing geographic attributes. Wikipedia provides natural textual contexts, while Wikidata offers structured data such as coordinates, place types, and administrative divisions, which can serve as rich metadata for future extensions. Our experiments show that models trained on our dataset achieve strong performance not only on in-domain data, i.e., Wikipedia, but also on out-of-domain newspaper articles, and further confirm that hard negative mining substantially improves disambiguation among confusable candidates. Although the dataset focuses on Japanese, the construction method is language-agnostic and can be extended to other languages with sufficient Wikipedia and Wikidata coverage.</abstract>
<identifier type="citekey">nakatani-etal-2026-large</identifier>
<identifier type="doi">10.63317/2pv6oidqzqs9</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.606/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7644</start>
<end>7654</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Dataset for Linking-Based Geocoding
%A Nakatani, Hibiki
%A Yasui, Yuichiro
%A Wakamoto, Ryosuke
%A Ishii, Masayuki
%A Suizu, Tetsuhisa
%A Ouchi, Hiroki
%A Watanabe, Taro
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F nakatani-etal-2026-large
%X Linking-based geocoding is the task of linking location mentions in text to their corresponding entries in a geographic database (Geo-DB) and assigning precise coordinates. Although the task and its technology are essential for spatial information extraction, existing datasets are manually curated and lack sufficient data for training accurate models. To address this limitation, we automatically construct a large-scale dataset for linking-based geocoding by leveraging publicly available resources to generate data efficiently at scale. Specifically, we align location mentions in the first paragraphs of Japanese Wikipedia articles with their associated Wikidata entries containing geographic attributes. Wikipedia provides natural textual contexts, while Wikidata offers structured data such as coordinates, place types, and administrative divisions, which can serve as rich metadata for future extensions. Our experiments show that models trained on our dataset achieve strong performance not only on in-domain data, i.e., Wikipedia, but also on out-of-domain newspaper articles, and further confirm that hard negative mining substantially improves disambiguation among confusable candidates. Although the dataset focuses on Japanese, the construction method is language-agnostic and can be extended to other languages with sufficient Wikipedia and Wikidata coverage.
%R 10.63317/2pv6oidqzqs9
%U https://aclanthology.org/2026.lrec-1.606/
%U https://doi.org/10.63317/2pv6oidqzqs9
%P 7644-7654
Markdown (Informal)
[A Large-Scale Dataset for Linking-Based Geocoding](https://aclanthology.org/2026.lrec-1.606/) (Nakatani et al., LREC 2026)
ACL
- Hibiki Nakatani, Yuichiro Yasui, Ryosuke Wakamoto, Masayuki Ishii, Tetsuhisa Suizu, Hiroki Ouchi, and Taro Watanabe. 2026. A Large-Scale Dataset for Linking-Based Geocoding. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7644–7654, Palma de Mallorca, Spain. ELRA Language Resource Association.