Welcome to the website of HIPE evaluation campaigns.
HIPE is a series of evaluation campaigns on named entity processing on historical documents in multiple languages.
In 2026, HIPE shifts focus from named entity recognition to relation extraction, with an emphasis on identifying person–place relations in multilingual historical newspapers. Participants are asked to assess whether a person was ever at a given place (at) or present in the immediate context (isAt), based on textual evidence and temporal cues.
Building on a pilot study and prior editions, HIPE-2026 introduces a new three-way classification task, where systems must label each relation as true, plausible, or false. The CLEF lab includes two evaluation profiles — one prioritizing accuracy, the other rewarding efficiency and scalability. A surprise test set from a different domain supports evaluation of domain generalization.
As in previous editions, all datasets will be publicly released to support transparency, reusability, and continued research in historical text processing.
In 2022, we organize an extended evaluation campaign on NE processing on historical documents of various types and languages, hosted by CLEF. The new website for CLEF HIPE 2022 is available here.
In 2020, we organized a first successful evaluation campaign on named entity processing on historical newspapers in French, German and English. It was organized in the context of the impresso project and run as a CLEF 2020 Evaluation Lab.