Papers with ReliefWeb
Humanitarian Corpora for English, French and Spanish (2024.lrec-main)
Copied to clipboard
| Challenge: | et al., a leading database of humanitarian documents, compiled with ReliefWeb reports . documents selected with language identification and noise reduction techniques . authors present corpora of English, French and Spanish humanitarian documents . |
| Approach: | They present three corpora of English, French and Spanish humanitarian documents compiled with ReliefWeb reports . documents were tokenized, lemmatized, tagged by part of speech, and enriched with metadata . authors propose a project to develop a humanitarian dictionary with a focus on conceptual variation . |
| Outcome: | The corpora were compiled to satisfy the research needs of the Humanitarian Encyclopedia project with a focus on conceptual variation. |
Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study (2026.findings-acl)
Copied to clipboard
| Challenge: | Humanitarian crises generate large volumes of narrative situation reports describing interventions and evolving outcomes. |
| Approach: | They propose a large language model pipeline that extracts structured intervention-outcome records with direction and strength attributes. |
| Outcome: | The proposed pipeline extracts structured intervention-outcome records with direction and strength attributes. |