{"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":null,"primary_location":{"id":"doi: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":null,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.181.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130389997","display_name":"Benno Uthayasooriyar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benno Uthayasooriyar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087080982","display_name":"Antoine Ly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Ly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578794","display_name":"Franck Vermet","orcid":"https://orcid.org/0000-0003-3816-5401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franck Vermet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130396568","display_name":"Caio Corro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caio Corro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.385988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.4729999899864197,"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":0.4729999899864197,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.1356000006198883,"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/T10028","display_name":"Topic Modeling","score":0.11299999803304672,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3255000114440918},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/polar","display_name":"Polar","score":0.2718000113964081},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2712000012397766},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2703999876976013}],"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":1,"locations":[{"id":"doi: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":null,"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"}],"best_oa_location":{"id":"doi: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":null,"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":[{"display_name":"Climate action","score":0.5129526853561401,"id":"https://metadata.un.org/sdg/13"}],"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":[],"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":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}