Quantitative Information Extraction from Humanitarian Documents

TL;DR

This paper introduces a new annotated dataset and NLP pipeline for extracting quantitative information from humanitarian documents, improving accuracy in identifying key data like affected populations and aid amounts.

Contribution

It provides the first specialized dataset and a tailored extraction pipeline for quantitative data in humanitarian texts, enhancing information retrieval in emergency contexts.

Findings

Improved extraction accuracy over baseline models

Effective performance on documents from Dominican Republic and African countries

Public release of dataset and code for further research

Abstract

Humanitarian action is accompanied by a mass of reports, summaries, news, and other documents. To guide its activities, important information must be quickly extracted from such free-text resources. Quantities, such as the number of people affected, amount of aid distributed, or the extent of infrastructure damage, are central to emergency response and anticipatory action. In this work, we contribute an annotated dataset for the humanitarian domain for the extraction of such quantitative information, along side its important context, including units it refers to, any modifiers, and the relevant event. Further, we develop a custom Natural Language Processing pipeline to extract the quantities alongside their units, and evaluate it in comparison to baseline and recent literature. The proposed model achieves a consistent improvement in the performance, especially in the documents pertaining to the Dominican Republic and select African countries. We make the dataset and code available to the research community to continue the improvement of NLP tools for the humanitarian domain.