Leave no Place Behind: Improved Geolocation in Humanitarian Documents

TL;DR

This paper enhances geolocation extraction from humanitarian texts by fine-tuning NER tools with domain-specific data and introducing a new geocoding method, significantly improving accuracy and reducing Western bias.

Contribution

It develops annotated datasets for fine-tuning NER models and proposes FeatureRank, a novel geocoding approach tailored for humanitarian documents.

Findings

NER performance improved up to F1=0.92 with domain data

Using humanitarian data reduces Western location bias

More non-Western resources are needed for better model deployment

Abstract

Geographical location is a crucial element of humanitarian response, outlining vulnerable populations, ongoing events, and available resources. Latest developments in Natural Language Processing may help in extracting vital information from the deluge of reports and documents produced by the humanitarian sector. However, the performance and biases of existing state-of-the-art information extraction tools are unknown. In this work, we develop annotated resources to fine-tune the popular Named Entity Recognition (NER) tools Spacy and roBERTa to perform geotagging of humanitarian texts. We then propose a geocoding method FeatureRank which links the candidate locations to the GeoNames database. We find that not only does the humanitarian-domain data improves the performance of the classifiers (up to F1 = 0.92), but it also alleviates some of the bias of the existing tools, which erroneously favor locations in the Western countries. Thus, we conclude that more resources from non-Western documents are necessary to ensure that off-the-shelf NER systems are suitable for the deployment in the humanitarian sector.