HUMAID-NER dataset for disaster tweet NER and event classification
HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning
This dataset and framework are valuable for researchers and developers working on AI applications for humanitarian response, as they provide a new resource for training models to extract structured information from social media during disasters.
A new dataset called HUMAID-NER, built on the HumAID benchmark, provides 60,000 English disaster tweets with span-level entity annotations for ten entity types.
It introduces a multitask learning framework using a shared RoBERTa-large encoder to perform both named entity recognition and event classification.
The system achieves an NER span micro-F1 of 0.841 and a classification macro-F1 of 0.
761 on the validation set.
HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning
Rapid extraction of structured information from social media is important for humanitarian response, yet existing disaster tweet resources mainly provide document-level category labels without span-level entity annotations. We introduce HUMAID-NER, the first named entity recognition dataset built on the HumAID benchmark, containing 60,000 English disaster tweets annotated in BIO format across ten operationally motivated entity types and yielding approximately 175,000 labelled entity spans. Annotations are generated through a reproducible three-stage hybrid pipeline combining a spaCy transformer model, disaster-domain EntityRuler patterns, and structured regular expressions with priority-based overlap resolution. We also propose a joint multitask learning framework that performs disaster-specific named entity recognition and humanitarian event classification using a shared RoBERTa-large encoder. To reduce task conflict during joint training, the model uses homoscedastic uncertainty weighting with learnable task parameters and a two-stage training schedule that freezes the lower 18 of 24 encoder layers in the second stage. On the HUMAID-NER validation set, the proposed system achieves NER span micro-F1 of 0.841 and classification macro-F1 of 0.761 simultaneously. A real-time web dashboard demonstrates end-to-end deployment. The dataset, models, and pipeline code are released to support reproducibility and future crisis informatics research.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include HUMAID-NER.
Source attribution: curated from arXiv cs.LG (@Aijaz Ali, Nazish Basir, Sarfaraz Nawaz, Danish Nazir Arain, Haris Ali).
