HIPE-2020

HIPE-2026 evaluation campaign: person-place relation extraction from multilingual historical texts

HIPE-2026 is the third edition of a shared-task evaluation series, shifting focus from named entity recognition to temporally grounded relation extraction across French, German, and English historical documents. Seventeen teams submitted over 40 runs, spanning large language models to lightweight classifiers, evaluated on predictive accuracy, computational efficiency, and cross-domain generalization. The campaign surfaces trade-offs between accuracy and robustness when processing noisy OCR text from 19th–20th century newspapers and early modern literary sources. Results provide a benchmark snapshot of the current state of historical relation extraction for cultural heritage applications.