{"id":"https://openalex.org/W2765085336","doi":"https://doi.org/10.1145/3148055.3148080","title":"Deep Understanding of a Document's Structure","display_name":"Deep Understanding of a Document's Structure","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2765085336","doi":"https://doi.org/10.1145/3148055.3148080","mag":"2765085336"},"language":"en","primary_location":{"id":"doi:10.1145/3148055.3148080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148055.3148080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3148055.3148080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3148055.3148080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101472406","display_name":"Muhammad Mahbubur Rahman","orcid":"https://orcid.org/0009-0008-4846-0248"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Mahbubur Rahman","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009972149","display_name":"Tim Finin","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Finin","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.4129,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7284309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9952999949455261,"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/T10028","display_name":"Topic Modeling","score":0.9952999949455261,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8554074168205261},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7619189023971558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6685684323310852},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5798690915107727},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5760701894760132},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5639641284942627},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5507652163505554},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5342674851417542},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49868273735046387},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4838082194328308},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4654774069786072},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4122036099433899},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40632379055023193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4019262194633484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.356446236371994},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11823955178260803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554074168205261},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7619189023971558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6685684323310852},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5798690915107727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5760701894760132},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5639641284942627},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5507652163505554},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5342674851417542},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49868273735046387},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4838082194328308},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4654774069786072},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4122036099433899},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40632379055023193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4019262194633484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.356446236371994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11823955178260803},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3148055.3148080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148055.3148080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3148055.3148080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/11581","is_oa":false,"landing_page_url":"http://hdl.handle.net/11603/11581","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/m2pk07558","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2pk07558","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.1145/3148055.3148080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148055.3148080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3148055.3148080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2103951337","display_name":"STTR Phase I:  SunDIAL: Slot DIscovery And Linking","funder_award_id":"1549697","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2765085336.pdf","grobid_xml":"https://content.openalex.org/works/W2765085336.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1490140361","https://openalex.org/W1511676561","https://openalex.org/W1525595230","https://openalex.org/W1530730108","https://openalex.org/W1880262756","https://openalex.org/W2005173844","https://openalex.org/W2026131180","https://openalex.org/W2045738181","https://openalex.org/W2052721056","https://openalex.org/W2055408294","https://openalex.org/W2061598441","https://openalex.org/W2079525773","https://openalex.org/W2088171019","https://openalex.org/W2099775103","https://openalex.org/W2101234009","https://openalex.org/W2118030626","https://openalex.org/W2121316417","https://openalex.org/W2135085165","https://openalex.org/W2135164809","https://openalex.org/W2137640092","https://openalex.org/W2143017621","https://openalex.org/W2153635508","https://openalex.org/W2166633748","https://openalex.org/W2271840356","https://openalex.org/W2953320089","https://openalex.org/W2997591727"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Current":[0],"language":[1,156,166],"understanding":[2,157],"approaches":[3],"focus":[4],"on":[5],"small":[6],"documents,":[7],"such":[8],"as":[9],"newswire":[10],"articles,":[11],"blog":[12],"posts,":[13],"product":[14],"reviews":[15],"and":[16,21,33,51,65,71,86,139,155,165],"discussion":[17],"forum":[18],"discussions.":[19],"Understanding":[20],"extracting":[22,87],"information":[23,57,108,160],"from":[24,115],"large":[25,49],"documents":[26,70,93],"like":[27],"legal":[28],"briefs,":[29],"proposals,":[30],"technical":[31],"manuals":[32],"research":[34,83],"articles":[35,114],"is":[36,84],"still":[37],"a":[38,43,48,105,110,122,131,148],"challenging":[39],"task.":[40],"We":[41,60,101,141],"describe":[42],"framework":[44],"that":[45,120,143],"can":[46],"analyze":[47],"document":[50],"help":[52],"people":[53],"to":[54,62],"locate":[55],"desired":[56],"in":[58],"it.":[59],"aim":[61],"automatically":[63],"identify":[64],"classify":[66],"different":[67],"sections":[68],"of":[69,81,91,107,112,125,133],"understand":[72],"their":[73],"purpose":[74],"within":[75],"the":[76,88,116,152],"document.":[77],"A":[78],"key":[79],"contribution":[80],"our":[82],"modeling":[85,167],"logical":[89],"structure":[90],"electronic":[92],"using":[94],"machine":[95,153],"learning":[96,154],"techniques,":[97],"including":[98,130],"deep":[99],"learning.":[100],"also":[102],"make":[103],"available":[104],"dataset":[106,145],"about":[109],"collection":[111,119],"scholarly":[113],"arXiv":[117],"eprints":[118],"includes":[121],"wide":[123],"range":[124],"metadata":[126],"for":[127,151,159],"each":[128],"article,":[129],"table":[132],"contents,":[134],"section":[135,137],"labels,":[136],"summarizations":[138],"more.":[140],"hope":[142],"this":[144],"will":[146],"be":[147],"useful":[149],"resource":[150],"communities":[158],"retrieval,":[161],"content-based":[162],"question":[163],"answering":[164],"tasks.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}