<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uthayasooriyar-etal-2026-docpolarbert">
    <titleInfo>
        <title>DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Benno</namePart>
        <namePart type="family">Uthayasooriyar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antoine</namePart>
        <namePart type="family">Ly</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Franck</namePart>
        <namePart type="family">Vermet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caio</namePart>
        <namePart type="family">Corro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-380-7</identifier>
    </relatedItem>
    <abstract>We propose a novel self-attention mechanism for document understanding that takes into account text block positions in relative polar coordinate system rather than the Cartesian one. Based on this mechanism, we build DocPolarBERT, a layout-aware BERT model for document understanding that eliminates the need for absolute 2D positional embeddings. Despite being pre-trained on a dataset more than six times smaller than the widely used IIT-CDIP corpus, DocPolarBERT achieves state-of-the-art results. These results demonstrate that a carefully designed attention mechanism can compensate for reduced pre-training data, offering an efficient and effective alternative for document understanding.</abstract>
    <identifier type="citekey">uthayasooriyar-etal-2026-docpolarbert</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-long.181/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>3897</start>
            <end>3907</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures
%A Uthayasooriyar, Benno
%A Ly, Antoine
%A Vermet, Franck
%A Corro, Caio
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F uthayasooriyar-etal-2026-docpolarbert
%X We propose a novel self-attention mechanism for document understanding that takes into account text block positions in relative polar coordinate system rather than the Cartesian one. Based on this mechanism, we build DocPolarBERT, a layout-aware BERT model for document understanding that eliminates the need for absolute 2D positional embeddings. Despite being pre-trained on a dataset more than six times smaller than the widely used IIT-CDIP corpus, DocPolarBERT achieves state-of-the-art results. These results demonstrate that a carefully designed attention mechanism can compensate for reduced pre-training data, offering an efficient and effective alternative for document understanding.
%U https://aclanthology.org/2026.eacl-long.181/
%P 3897-3907

Markdown (Informal)

[DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures](https://aclanthology.org/2026.eacl-long.181/) (Uthayasooriyar et al., EACL 2026)

• DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures (Uthayasooriyar et al., EACL 2026)

ACL

• Benno Uthayasooriyar, Antoine Ly, Franck Vermet, and Caio Corro. 2026. DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3897–3907, Rabat, Morocco. Association for Computational Linguistics.