{"id":"https://openalex.org/W4404782946","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.65","title":"DocHieNet: A Large and Diverse Dataset for Document Hierarchy Parsing","display_name":"DocHieNet: A Large and Diverse Dataset for Document Hierarchy Parsing","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782946","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.65"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.65","pdf_url":"https://aclanthology.org/2024.emnlp-main.65.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.65.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039720488","display_name":"Hangdi Xing","orcid":"https://orcid.org/0000-0002-1770-005X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hangdi Xing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069902262","display_name":"Changxu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changxu Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038757890","display_name":"Feiyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyu Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005709630","display_name":"Zirui Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zirui Shao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117233230","display_name":"Zhi Yu","orcid":"https://orcid.org/0009-0001-8608-5628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750527","display_name":"Qi Zheng","orcid":"https://orcid.org/0009-0001-3822-2616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669593","display_name":"Cong Yao","orcid":"https://orcid.org/0000-0001-6564-4796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Yao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5039720488"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0034,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8142899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1129","last_page":"1142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9801999926567078,"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":0.9801999926567078,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.928600013256073,"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/parsing","display_name":"Parsing","score":0.8385254144668579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018295764923096},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7859909534454346},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48441746830940247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4574619233608246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43757376074790955}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8385254144668579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018295764923096},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7859909534454346},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48441746830940247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4574619233608246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43757376074790955},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.65","pdf_url":"https://aclanthology.org/2024.emnlp-main.65.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.65","pdf_url":"https://aclanthology.org/2024.emnlp-main.65.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1122440035","display_name":null,"funder_award_id":"62372408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782946.pdf","grobid_xml":"https://content.openalex.org/works/W4404782946.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W962203960","https://openalex.org/W2026999166","https://openalex.org/W579810227","https://openalex.org/W1996802783","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W1502858101","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Parsing":[0],"documents":[1,44],"from":[2],"pixels,":[3],"such":[4],"as":[5,98],"pictures":[6],"and":[7,24,76,89,117,135,150],"scanned":[8],"PDFs,":[9],"into":[10],"hierarchical":[11],"structures":[12],"is":[13,60],"extensively":[14],"demanded":[15],"in":[16,64,131,138],"the":[17,27,65,86,125,133,144],"daily":[18],"routines":[19],"of":[20,45,56,127,146],"data":[21,87],"storage,":[22],"retrieval":[23],"understanding.However,":[25],"previously":[26],"research":[28],"on":[29],"this":[30,70],"topic":[31],"has":[32],"been":[33],"largely":[34],"hindered":[35],"since":[36],"most":[37],"existing":[38],"datasets":[39],"are":[40,51],"small-scale,":[41],"or":[42],"contain":[43],"only":[46],"a":[47,54,61,74,95,99,106],"single":[48],"type,":[49],"which":[50],"characterized":[52],"by":[53],"lack":[55],"document":[57,78],"diversity.Moreover,":[58],"there":[59],"significant":[62],"discrepancy":[63],"annotation":[66],"standards":[67],"across":[68],"datasets.In":[69],"paper,":[71],"we":[72,104,142],"introduce":[73],"large":[75],"diverse":[77],"hierarchy":[79],"parsing":[80],"(DHP)":[81],"dataset":[82,149],"to":[83,93,111],"compensate":[84],"for":[85],"scarcity":[88],"inconsistency":[90],"problem.We":[91],"aim":[92],"set":[94],"new":[96,107],"standard":[97],"more":[100],"practical,":[101],"long-standing":[102],"benchmark.Meanwhile,":[103],"present":[105],"DHP":[108],"framework":[109],"designed":[110],"grasp":[112],"both":[113],"fine-grained":[114],"text":[115],"content":[116],"coarsegrained":[118],"pattern":[119],"at":[120],"layout":[121],"element":[122],"level,":[123],"enhancing":[124],"capacity":[126],"pre-trained":[128],"text-layout":[129],"models":[130],"handling":[132],"multi-page":[134],"multi-level":[136],"challenges":[137],"DHP.Through":[139],"exhaustive":[140],"experiments,":[141],"validate":[143],"effectiveness":[145],"our":[147],"proposed":[148],"method":[151],"1":[152],".":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}