Geo-entity linking is the task of linking a location mention to the real-world geographic location. In this paper we explore the challenging task of geo-entity linking for noisy, multilingual social media data. There are few open-source multilingual geo-entity linking tools available and existing ones are often rule-based, which break easily in social media settings, or LLM-based, which are too expensive for large-scale datasets. We present a method which represents real-world locations as averaged embeddings from labeled user-input location names and allows for selective prediction via an interpretable confidence score. We show that our approach improves geo-entity linking on a global and multilingual social media dataset, and discuss progress and problems with evaluating at different geographic granularities.
@article{arxiv.2404.18784,
title = {Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input},
author = {Tessa Masis and Brendan O'Connor},
journal= {arXiv preprint arXiv:2404.18784},
year = {2024}
}