{"id":"https://openalex.org/W7140110720","doi":"https://doi.org/10.18653/v1/2026.eacl-industry.28","title":"OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets","display_name":"OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140110720","doi":"https://doi.org/10.18653/v1/2026.eacl-industry.28"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-industry.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-industry.28","pdf_url":"https://aclanthology.org/2026.eacl-industry.28.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 5: Industry Track)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-industry.28.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122228782","display_name":"Jiyuan Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiyuan Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130396718","display_name":"Yuan Peiyue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Peiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130347590","display_name":"Atin Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atin Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130340363","display_name":"Yifan Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Mai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002373633","display_name":"Daniel Dahlmeier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Dahlmeier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.38624718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.815500020980835,"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":0.815500020980835,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.029100000858306885,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.017100000753998756,"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/information-extraction","display_name":"Information extraction","score":0.5228999853134155},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.367000013589859},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26179999113082886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2572999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764000058174133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46140000224113464},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-industry.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-industry.28","pdf_url":"https://aclanthology.org/2026.eacl-industry.28.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 5: Industry Track)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-industry.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-industry.28","pdf_url":"https://aclanthology.org/2026.eacl-industry.28.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 5: Industry Track)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140110720.pdf","grobid_xml":"https://content.openalex.org/works/W7140110720.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Jiyuan":[0],"Shen,":[1],"Yuan":[2],"Peiyue,":[3],"Atin":[4],"Ghosh,":[5],"Yifan":[6],"Mai,":[7],"Daniel":[8],"Dahlmeier.":[9],"Proceedings":[10],"of":[11,15,19],"the":[12,16,20],"19th":[13],"Conference":[14],"European":[17],"Chapter":[18],"Association":[21],"for":[22],"Computational":[23],"Linguistics":[24],"(Volume":[25],"5:":[26],"Industry":[27],"Track).":[28],"2026.":[29]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
