@inproceedings{uthayasooriyar-etal-2026-docpolarbert,
    title = "{D}oc{P}olar{BERT}: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures",
    author = "Uthayasooriyar, Benno  and
      Ly, Antoine  and
      Vermet, Franck  and
      Corro, Caio",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.181/",
    pages = "3897--3907",
    ISBN = "979-8-89176-380-7",
    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."
}