The HIPE-2026 evaluation campaign focused on extracting person-place relationships from multilingual historical texts, building upon previous HIPE editions that concentrated on named entity recognition. This year's challenge involved identifying two types of temporal relationships: '$at$' (person was at a place before publication) and '$isAt$' (person was at a place contemporaneous with publication). The evaluation considered accuracy, computational efficiency, and cross-domain generalization across French, German, and English texts from the 19th and 20th centuries, as well as early modern French literature. AI
IMPACT This research advances methods for extracting structured information from historical texts, potentially improving knowledge graph construction and digital humanities research.
RANK_REASON The cluster describes the results of an academic evaluation campaign and associated research paper.
- alphaXiv
- CatalyzeX
- DagsHub
- early modern period
- English
- French
- German
- Gotit.pub
- HIPE-2020
- HIPE-2022
- HIPE-2026
- Hugging Face
- ScienceCast
- twentieth centuries
- Influence Flower
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →