Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input

TL;DR

This paper introduces a scalable, multilingual geo-entity linking method for noisy social media data, utilizing averaged location embeddings and confidence scores to improve accuracy across diverse geographic regions.

Contribution

It presents a novel approach that leverages averaged embeddings and interpretable confidence scores, addressing limitations of rule-based and LLM-based tools in social media contexts.

Findings

Improved geo-entity linking accuracy on global multilingual social media data.

Effective handling of noisy, multilingual location mentions.

Discussion of evaluation challenges at different geographic granularities.

Abstract

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.