{"id":"https://openalex.org/W4404822953","doi":"https://doi.org/10.1007/978-981-97-8367-0_23","title":"DLUE: Benchmarking Document Language Understanding","display_name":"DLUE: Benchmarking Document Language Understanding","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4404822953","doi":"https://doi.org/10.1007/978-981-97-8367-0_23"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-97-8367-0_23","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-97-8367-0_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-981-97-8367-0_23","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070696282","display_name":"R. F. Xu","orcid":"https://orcid.org/0000-0001-8145-6453"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxi Xu","raw_affiliation_strings":["Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 101408, China"],"affiliations":[{"raw_affiliation_string":"Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090777164","display_name":"Hongyu Lin","orcid":"https://orcid.org/0009-0001-5857-9663"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Lin","raw_affiliation_strings":["Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051575106","display_name":"Xinyan Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Guan","raw_affiliation_strings":["Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 101408, China"],"affiliations":[{"raw_affiliation_string":"Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211417","display_name":"Yingfei Sun","orcid":"https://orcid.org/0000-0003-0615-2569"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingfei Sun","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, 101408, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101652785","display_name":"Le Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Sun","raw_affiliation_strings":["Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103211417"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46579464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.8738539218902588},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7786943912506104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5234015583992004},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4372623562812805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3938525915145874},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3592596650123596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738539218902588},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7786943912506104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5234015583992004},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4372623562812805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3938525915145874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3592596650123596},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-97-8367-0_23","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-97-8367-0_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-981-97-8367-0_23","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-97-8367-0_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2075873247","https://openalex.org/W2299976354","https://openalex.org/W2562910494","https://openalex.org/W2923014074","https://openalex.org/W2943552823","https://openalex.org/W2955041501","https://openalex.org/W2963341956","https://openalex.org/W2963926728","https://openalex.org/W2963963993","https://openalex.org/W2970742161","https://openalex.org/W2971141916","https://openalex.org/W3008736151","https://openalex.org/W3034284720","https://openalex.org/W3103553006","https://openalex.org/W3153603860","https://openalex.org/W3161820423","https://openalex.org/W3169283738","https://openalex.org/W3170490008","https://openalex.org/W3199177860","https://openalex.org/W3201977280","https://openalex.org/W4225661174","https://openalex.org/W4226072238","https://openalex.org/W4285294723","https://openalex.org/W4385573804","https://openalex.org/W4389519019","https://openalex.org/W6600109629","https://openalex.org/W6739901393","https://openalex.org/W6781533629","https://openalex.org/W6785783668","https://openalex.org/W6858023062"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Understanding":[0,72],"documents":[1],"is":[2,15,122],"central":[3],"to":[4,21,110],"many":[5],"real-world":[6,130],"tasks":[7,85],"but":[8],"remains":[9],"a":[10,76,82],"challenging":[11],"topic.":[12],"Unfortunately,":[13],"there":[14],"no":[16],"well-established":[17,98],"consensus":[18],"on":[19,104],"how":[20],"comprehensively":[22],"evaluate":[23,96],"document":[24,42,52,54,57,61,91,120],"understanding":[25,43,121],"abilities,":[26,50],"which":[27,80],"significantly":[28],"hinders":[29],"the":[30,35,38,64,111],"fair":[31],"comparison":[32],"and":[33,60,90,101,106,117],"measuring":[34],"progress":[36],"of":[37,84],"field.":[39],"To":[40],"benchmark":[41],"researches,":[44],"this":[45],"paper":[46],"summarizes":[47],"four":[48],"representative":[49,102],"i.e.,":[51],"classification,":[53],"structural":[55],"analysis,":[56],"information":[58],"extraction,":[59],"transcription.":[62],"Under":[63],"new":[65,77],"evaluation":[66],"framework,":[67],"we":[68],"propose":[69],"Document":[70],"Language":[71],"Evaluation":[73],"\u2013":[74],"DLUE,":[75,105],"task":[78],"suite":[79],"covers":[81],"wide-range":[83],"in":[86,128],"various":[87],"forms,":[88],"domains":[89],"genres.":[92],"We":[93],"also":[94],"systematically":[95],"six":[97],"transformer":[99],"models":[100],"LLMs":[103],"find":[107],"that":[108],"due":[109],"lengthy":[112],"content,":[113],"complicated":[114],"underlying":[115],"structure":[116],"dispersed":[118],"knowledge,":[119],"still":[123],"far":[124],"from":[125],"being":[126],"solved":[127],"complex":[129],"scenarios.":[131]},"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
