%0 Conference Proceedings
%T Overview of DocILE 2023: Document Information Localization and Extraction
%A Stepan Simsa
%A Michal Uricar
%A Milan Sulc
%A Yash Patel
%A Ahmed Hamdi
%A Matej Kocian
%A Matyas Skalicky
%A Jiri Matas
%A Antoine Doucet
%A Mickael Coustaty
%A Dimosthenis Karatzas
%B International Conference of the Cross-Language Evaluation Forum for European Languages
%D 2023
%V 14163
%F Stepan Simsa2023
%O DAG
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3924), last updated on Wed, 24 Jan 2024 15:05:49 +0100
%X 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.
%K Information Extraction
%K Computer Vision
%K Natural Language Processing
%K Optical Character Recognition
%K Document Understanding
%U https://link.springer.com/chapter/10.1007/978-3-031-42448-9_21
%U http://dx.doi.org/https://doi.org/10.1007/978-3-031-42448-9_21
%P 276–293