A Benchmark of Named Entity Recognition Approaches in Historical Documents Application to 19th Century French Directories
Résumé
Named entity recognition (NER) is a necessary step in many pipelines targeting historical documents. Indeed, such natural language processing techniques identify which class each text token belongs to, e.g. "person name", "location", "number". Introducing a new public dataset built from 19th century French directories, we first assess how noisy modern, off-the-shelf OCR are. Then, we compare modern CNNand Transformer-based NER techniques which can be reasonably used in the context of historical document analysis. We measure their requirements in terms of training data, the effects of OCR noise on their performance, and show how Transformer-based NER can benefit from unsupervised pre-training and supervised fine-tuning on noisy data. Results can be reproduced using resources available at https://github.com/ soduco/paper-ner-bench-das22.
Fichier principal
preprint_das_2022_abadie_carlinet_chazalon_dumenieu.pdf (949)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|
![]()
Cite 10.5281/zenodo.6394464 A Dataset of French Trade Directories from the 19th Century (FTD), https://doi.org/10.5281/zenodo.6394464
![]()
Cite 10.5281/zenodo.6576008 [Data] NER models from "A Benchmark of Named Entity Recognition Approaches in Historical Documents Application to 19th Century French Directories", DAS22 workshop on document analysis systems., https://doi.org/10.5281/zenodo.6576008
![]()
Référence hal-04421578 Autre Nathalie Abadie, Stéphane Baciocchi, Edwin Carlinet, Joseph Chazalon, Pascal Cristofoli, et al.. [Données] Un jeu de données d'annuaires du commerce français de 19ème siècle. 2022, ⟨10.5281/zenodo.6394464⟩. ⟨hal-04421578⟩
Jeu de données produit pour cet article
![]()
Référence hal-04421586 Autre Nathalie Abadie, Edwin Carlinet, Joseph Chazalon, Bertrand Duménieu. [Données] Modèles de NER produits pour l'article "A Benchmark of Named Entity Recognition Approaches in Historical Documents Application to 19th Century French Directories", publiés lors de l'atelier d'analyse de documents DAS22.. 2022, ⟨10.5281/zenodo.6576008⟩. ⟨hal-04421586⟩
Modèles de NER produits pour cet article