Communication Dans Un Congrès Année : 2023

Overview of DocILE 2023: Document Information Localization and Extraction

Štěpán Šimsa
Michal Uřičář
Milan Šulc
Yash Patel
Matěj Kocián
Matyáš Skalický
Jiří Matas

Résumé

This paper provides an overview of the DocILE 2023 Competition, its tasks, participant submissions, the competition results and possible future research directions. This first edition of the competition focused on two Information Extraction tasks, Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR). Both of these tasks require detection of pre-defined categories of information in business documents. The second task additionally requires correctly grouping the information into tuples, capturing the structure laid out in the document. The competition used the recently published DocILE dataset and benchmark that stays open to new submissions. The diversity of the participant solutions indicates the potential of the dataset as the submissions included pure Computer Vision, pure Natural Language Processing, as well as multi-modal solutions and utilized all of the parts of the dataset, including the annotated, synthetic and unlabeled subsets.

Fichier non déposé

Dates et versions

hal-04678403 , version 1 (27-08-2024)

Identifiants

Citer

Štěpán Šimsa, Michal Uřičář, Milan Šulc, Yash Patel, Ahmed Hamdi, et al.. Overview of DocILE 2023: Document Information Localization and Extraction. CLEF 2023, Sep 2023, Thessaloniki, Greece. pp.276-293, ⟨10.1007/978-3-031-42448-9_21⟩. ⟨hal-04678403⟩
97 Consultations
0 Téléchargements

Altmetric

Partager

  • More