Impact of OCR errors on the use of digital libraries Towards a be er access to information - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Impact of OCR errors on the use of digital libraries Towards a be er access to information

Résumé

Digital collections are increasingly used for a variety of purposes. In Europe only, we can conservatively estimate that tens of thousands of users consult digital libraries daily. e usages are o en motivated by qualitative and quantitative research. However, caution must be advised as most digitized documents are indexed through their OCRed version, which is far from perfect, especially for ancient documents. In this paper, we aim to estimate the impact of OCR errors on the use of a major online platform: e Gallica digital library from the National Library of France. It accounts for more than 100M OCRed documents and receives 80M search queries every year. In this context, we introduce two main contributions. First, an original corpus of OCRed documents composed of 12M characters along with the corresponding gold standard is presented and provided, with an equal share of English-and French-wri en documents. Next, statistics on OCR errors have been computed thanks to a novel alignment method introduced in this paper. Making use of all the user queries submi ed to the Gallica portal over 4 months, we take advantage of our error model to propose an indicator for predicting the relative risk that queried terms mismatch targeted resources due to OCR errors, underlining the critical extent to which OCR quality impacts on digital library access.
Fichier principal
Vignette du fichier
07991582(1).pdf (603.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03025508 , version 1 (26-11-2020)

Identifiants

Citer

Guillaume Chiron, Antoine Doucet, Mickaël Coustaty, Muriel Visani, Jean-Philippe Moreux. Impact of OCR errors on the use of digital libraries Towards a be er access to information. 2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL), Jun 2017, Toronto, Canada. ⟨10.1109/JCDL.2017.7991582⟩. ⟨hal-03025508⟩
214 Consultations
342 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More