×
The HIPE corpus [4] is a collection of digitized documents covering three different languages: English, French, and German. The documents come from archives of ...
Knowledge-based Contexts for Historical Named Entity Recognition & Linking · Computer Science, History. Conference and Labs of the Evaluation Forum · 2022.
This paper summarizes the participation of the L3i laboratory of the University of La Rochelle in the Identifying Historical People, Places, and other Entities ...
This paper adopts two main evaluation objectives: named entity recognition (NER) and sentence splitting (SenS).
In this survey, we present the array of challenges posed by historical documents to NER, inventory existing resources, describe the main approaches deployed so ...
Robust named entity recognition and linking on historical multilingual documents. E Boros, EL Pontes, LA Cabrera-Diego, A Hamdi, JG Moreno, N Sidère ...
A multilingual dataset for named entity recognition, entity linking and stance detection in historical newspapers
People also ask
This paper describes our submission to the CLEF HIPE 2020 shared task on identifying named entities in multi-lingual historical news- papers in French, German ...
May 25, 2024 · All three models outperform a contemporary multilingual baseline by a large margin on historical test data. Keywords: named entity recognition, ...
Missing: Robust | Show results with:Robust
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets.