{"id":"https://openalex.org/W7140075698","doi":"https://doi.org/10.18653/v1/2026.eacl-long.265","title":"ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images","display_name":"ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140075698","doi":"https://doi.org/10.18653/v1/2026.eacl-long.265"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.265","doi":"https://doi.org/10.18653/v1/2026.eacl-long.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.265","pdf_url":"https://aclanthology.org/2026.eacl-long.265.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.eacl-long.265.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093650437","display_name":"Mathieu Sibue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Sibue","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125964957","display_name":"Andres Mu\u00f1oz Garza","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9s Mu\u00f1oz Garza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125981568","display_name":"Samuel Mensah","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Mensah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125951086","display_name":"Pranav Shetty","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pranav Shetty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125937581","display_name":"Zhiqiang Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134442664","display_name":"Xiaomo Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaomo Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X","observed_orcids":["https://orcid.org/0000-0001-6738-238X","https://orcid.org/0000-0001-5355-1912"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.16170166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5669","last_page":"5688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9922000169754028,"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":0.9922000169754028,"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":0.004000000189989805,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.8949999809265137},{"id":"https://openalex.org/keywords/document-images","display_name":"scanned documents","score":0.7950000166893005},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.8519999980926514},{"id":"https://openalex.org/keywords/document-understanding","display_name":"document understanding","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437999963760376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.265","doi":"https://doi.org/10.18653/v1/2026.eacl-long.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.265","pdf_url":"https://aclanthology.org/2026.eacl-long.265.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.265","doi":"https://doi.org/10.18653/v1/2026.eacl-long.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.265","pdf_url":"https://aclanthology.org/2026.eacl-long.265.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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140075698.pdf","grobid_xml":"https://content.openalex.org/works/W7140075698.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100647188","https://openalex.org/W7166862764","https://openalex.org/W4239730519","https://openalex.org/W2243709995","https://openalex.org/W4403552889","https://openalex.org/W2970947087","https://openalex.org/W90133363","https://openalex.org/W6996853521","https://openalex.org/W4413390404","https://openalex.org/W7110612299"],"abstract_inverted_index":{"Mathieu":[0],"Sibue,":[1],"Andr\u00e9s":[2],"Mu\u00f1oz":[3],"Garza,":[4],"Samuel":[5],"Mensah,":[6],"Pranav":[7],"Shetty,":[8],"Zhiqiang":[9],"Ma,":[10],"Xiaomo":[11],"Liu,":[12],"Manuela":[13],"Veloso.":[14],"Proceedings":[15],"of":[16,20,24],"the":[17,21,25],"19th":[18],"Conference":[19],"European":[22],"Chapter":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"1:":[31],"Long":[32],"Papers).":[33],"2026.":[34]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-16T00:00:00"}