A Text Embedding Model with Contrastive Example Mining for Point-of-Interest Geocoding
Hibiki Nakatani, Hiroki Teranishi, Shohei Higashiyama, Yuya Sawada, Hiroki Ouchi, Taro Watanabe
Abstract
Geocoding is a fundamental technique that links location mentions to their geographic positions, which is important for understanding texts in terms of where the described events occurred. Unlike most geocoding studies that targeted coarse-grained locations, we focus on geocoding at a fine-grained point-of-interest (POI) level. To address the challenge of finding appropriate geo-database entries from among many candidates with similar POI names, we develop a text embedding-based geocoding model and investigate (1) entry encoding representations and (2) hard negative mining approaches suitable for enhancing the model’s disambiguation ability. Our experiments show that the second factor significantly impact the geocoding accuracy of the model.
BibTeX
@inproceedings{nakatani-etal-2025-text,
title = "A Text Embedding Model with Contrastive Example Mining for Point-of-Interest Geocoding",
author = "Nakatani, Hibiki and
Teranishi, Hiroki and
Higashiyama, Shohei and
Sawada, Yuya and
Ouchi, Hiroki and
Watanabe, Taro",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.486/",
pages = "7279--7291"
}