Natural language processing for humanitarian action: Opportunities, challenges, and the path toward humanitarian NLP

Frontiers in Big Data · 5 authors, 4 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

Full summary

661 CHARS

The authors identify how NLP techniques could help humanitarian organizations leverage unstructured text data—such as internal reports, need overviews, news media, social media, and survey interviews—to monitor, prepare for, and respond to crises at scale. Several key challenges are highlighted: state-of-the-art deep learning models require large pre-training data that is rarely available for low-resource languages spoken by affected populations; pretrained models can absorb and reproduce gender and racial biases present in training data; and modern NLP models function as black boxes, making accountability difficult in high-stakes humanitarian contexts.

STUDY TYPE

narrative_review

SPECIALTY

research methods

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10080095

Natural language processing for humanitarian action: Opportunities, challenges, and the path toward humanitarian NLP

Frontiers in Big Data

READ THE FULL PAPER

ABSTRACT

Abstract Natural language processing (NLP) is a rapidly evolving field at the intersection of linguistics, computer science, and artificial intelligence, which is concerned with developing methods to process and generate language at scale. Modern NLP tools have the potential to support humanitarian action at multiple stages of the humanitarian response cycle. Both internal reports, secondary text data (e.g., social media data, news media articles, or interviews with affected individuals), and external-facing documents like Humanitarian Needs Overviews (HNOs) encode information relevant to monitoring, anticipating, or responding to humanitarian crises. Yet, lack of awareness of the concrete opportunities offered by state-of-the-art techniques, as well as constraints posed by resource scarcity, limit adoption of NLP tools in the humanitarian sector. This paper provides a pragmatically-minded primer to the emerging field of humanitarian NLP, reviewing existing initiatives in the space of humanitarian NLP, highlighting potentially impactful applications of NLP in the humanitarian sector, and describing criteria, challenges, and potential solutions for large-scale adoption. In addition, as one of the main bottlenecks is the lack of data and standards for this domain, we present recent initiatives (the DEEP and HumSet ) which are directly aimed at addressing these gaps. With this work, we hope to motivate humanitarians and NLP experts to create long-term impact-driven synergies and to co-develop an ambitious roadmap for the field. Keywords: NLP, humanitarian response, machine learning, transformers, social good

CITATION EXPORT

Roberta Rocca, Nicolò Tamagnone, Selim Fekih et al.. Natural language processing for humanitarian action: Opportunities, challenges, and the path toward humanitarian NLP. Frontiers in Big Data. (2023). https://doi.org/10.3389/fdata.2023.1082787

AUTHORS

5 · 4 CENTRES

Roberta Rocca, Nicolò Tamagnone, Selim Fekih, Ximena Contla, Navid Rekabsaz

1Department of Culture, Cognition and Computation, Aarhus University, Aarhus, Denmark
2Data Friendly Space, Richmond, VA, United States
3Institute of Computational Perception, Johannes Kepler University, Linz, Austria
4Linz Institute of Technology, AI Lab, Linz, Austria