Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories - ANR - Agence nationale de la recherche Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories

Résumé

When extracting structured data from repetitively organized documents, such as dictionaries, directories, or even newspapers, a key challenge is to correctly segment what constitutes the basic text regions for the target database. Traditionally, such a problem was tackled as part of the layout analysis and was mostly based on visual clues for dividing (top-down) approaches. Some agglomerating (bottom-up) approaches started to consider textual information to link similar contents, but they required a proper over-segmentation of ne-grained units. In this work, we propose a new pragmatic approach whose eciency is demonstrated on 19 th century French Trade Directories. We propose to consider two sub-problems: coarse layout detection (text columns and reading order), which is assumed to be eective and not detailed here, and a ne-grained entry separation stage for which we propose to adapt a state-of-the-art Named Entity Recognition (NER) approach. By injecting special visual tokens, coding, for instance, indentation or breaks, into the token stream of the language model used for NER purpose, we can leverage both textual and visual knowledge simultaneously. Code, data, results and models are available at https://github.com/soduco/ paper-entryseg-icdar23-code, https://huggingface.co/HueyNemud/ (icdar23-entrydetector* variants).
Fichier principal
Vignette du fichier
main.pdf (1.44 Mo) Télécharger le fichier

Dates et versions

hal-03994702 , version 1 (17-02-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

  • HAL Id : hal-03994702 , version 1

Citer

Bertrand Duménieu, Edwin Carlinet, Nathalie Abadie, Joseph Chazalon. Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories. 2023. ⟨hal-03994702⟩
18 Consultations
55 Téléchargements

Partager

Gmail Facebook X LinkedIn More