{"id":"https://openalex.org/W7140107208","doi":"https://doi.org/10.18653/v1/2026.eacl-long.181","title":"DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures","display_name":"DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140107208","doi":"https://doi.org/10.18653/v1/2026.eacl-long.181"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.181","doi":"https://doi.org/10.18653/v1/2026.eacl-long.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.181","pdf_url":"https://aclanthology.org/2026.eacl-long.181.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.eacl-long.181.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080197972","display_name":"Benno Uthayasooriyar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119023","display_name":"Laboratoire de Math\u00e9matiques de Bretagne Atlantique","ror":"https://ror.org/02ght4n58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802204017","https://openalex.org/I4210119023","https://openalex.org/I4210141950","https://openalex.org/I4405260085"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benno Uthayasooriyar","raw_affiliation_strings":["Data Analytics Solutions , SCOR","Univ Brest , CNRS , UMR 6205 , LMBA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics Solutions , SCOR","institution_ids":[]},{"raw_affiliation_string":"Univ Brest , CNRS , UMR 6205 , LMBA","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087080982","display_name":"Antoine Ly","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Ly","raw_affiliation_strings":["Data Analytics Solutions , SCOR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics Solutions , SCOR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578794","display_name":"Franck Vermet","orcid":"https://orcid.org/0000-0003-3816-5401","observed_orcids":["https://orcid.org/0000-0003-3816-5401"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119023","display_name":"Laboratoire de Math\u00e9matiques de Bretagne Atlantique","ror":"https://ror.org/02ght4n58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802204017","https://openalex.org/I4210119023","https://openalex.org/I4210141950","https://openalex.org/I4405260085"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Vermet","raw_affiliation_strings":["Univ Brest , CNRS , UMR 6205 , LMBA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ Brest , CNRS , UMR 6205 , LMBA","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045551176","display_name":"Caio Corro","orcid":"https://orcid.org/0000-0001-7443-4109","observed_orcids":["https://orcid.org/0000-0001-7443-4109"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Caio Corro","raw_affiliation_strings":["INSA Rennes , IRISA , Inria , CNRS , Universit\u00e9 de Rennes"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA Rennes , IRISA , Inria , CNRS , Universit\u00e9 de Rennes","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I56067802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16497797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"Volume 1: Long Papers","issue":null,"first_page":"3897","last_page":"3907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/document-understanding","display_name":"document understanding","score":0.9340000152587891},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.8920000195503235},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.6570000052452087},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"document layout analysis","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5917999744415283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C29705727","wikidata":"https://www.wikidata.org/wiki/Q294562","display_name":"Polar","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26409998536109924},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.181","doi":"https://doi.org/10.18653/v1/2026.eacl-long.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.181","pdf_url":"https://aclanthology.org/2026.eacl-long.181.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.08606","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.08606","pdf_url":"https://arxiv.org/pdf/2507.08606","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05571266v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05571266v1","pdf_url":"https://hal.science/hal-05571266v1/file/Benno_2026.eacl-long.181.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Mar 2026, Rabat, Morocco. pp.3897-3907","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2507.08606","doi":"https://doi.org/10.48550/arxiv.2507.08606","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.08606","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.181","doi":"https://doi.org/10.18653/v1/2026.eacl-long.181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.181","pdf_url":"https://aclanthology.org/2026.eacl-long.181.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5129526853561401,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140107208.pdf","grobid_xml":"https://content.openalex.org/works/W7140107208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389518990","https://openalex.org/W3189592177","https://openalex.org/W3196553436","https://openalex.org/W4288804004","https://openalex.org/W4306178108","https://openalex.org/W3006883036","https://openalex.org/W3176851559","https://openalex.org/W3204562006","https://openalex.org/W4296878270","https://openalex.org/W3197942012"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,32,51,71],"novel":[3],"self-attention":[4],"mechanism":[5,75],"for":[6,36,43,78,88],"document":[7,37,89],"understanding":[8,38],"that":[9,39,70],"takes":[10],"into":[11],"account":[12],"text":[13],"block":[14],"positions":[15],"in":[16],"relative":[17],"polar":[18],"coordinate":[19],"system":[20],"rather":[21],"than":[22,54,58],"the":[23,41,59],"Cartesian":[24],"one.Based":[25],"on":[26,50],"this":[27],"mechanism,":[28],"we":[29],"build":[30],"DOCPO-LARBERT,":[31],"layout-aware":[33],"BERT":[34],"model":[35],"eliminates":[40],"need":[42],"absolute":[44],"2D":[45],"positional":[46],"embeddings.Despite":[47],"being":[48],"pre-trained":[49],"dataset":[52],"more":[53],"six":[55],"times":[56],"smaller":[57],"widely":[60],"used":[61],"IIT-CDIP":[62],"corpus,":[63],"DOCPOLARBERT":[64],"achieves":[65],"state-of-the-art":[66],"results.These":[67],"results":[68],"demonstrate":[69],"carefully":[72],"designed":[73],"attention":[74],"can":[76],"compensate":[77],"reduced":[79],"pre-training":[80],"data,":[81],"offering":[82],"an":[83],"efficient":[84],"and":[85],"effective":[86],"alternative":[87],"understanding.":[90]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-03-24T00:00:00"}