@InProceedings{StepanSimsa2023,
author="Stepan Simsa
and Michal Uricar
and Milan Sulc
and Yash Patel
and Ahmed Hamdi
and Matej Kocian
and Matyas Skalicky
and Jiri Matas
and Antoine Doucet
and Mickael Coustaty
and Dimosthenis Karatzas",
title="Overview of DocILE 2023: Document Information Localization and Extraction",
booktitle="International Conference of the Cross-Language Evaluation Forum for European Languages",
year="2023",
volume="14163",
pages="276--293",
optkeywords="Information Extraction",
optkeywords="Computer Vision",
optkeywords="Natural Language Processing",
optkeywords="Optical Character Recognition",
optkeywords="Document Understanding",
abstract="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.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3924), last updated on Wed, 24 Jan 2024 15:05:49 +0100",
doi="https://doi.org/10.1007/978-3-031-42448-9_21",
opturl="https://link.springer.com/chapter/10.1007/978-3-031-42448-9_21"
}