{"id":"https://openalex.org/W2753477019","doi":"https://doi.org/10.1145/3103010.3121043","title":"Automatic Knowledge Base Construction from Scholarly Documents","display_name":"Automatic Knowledge Base Construction from Scholarly Documents","publication_year":2017,"publication_date":"2017-08-31","ids":{"openalex":"https://openalex.org/W2753477019","doi":"https://doi.org/10.1145/3103010.3121043","mag":"2753477019"},"language":"en","primary_location":{"id":"doi:10.1145/3103010.3121043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004860693","display_name":"Rabah A. Al-Zaidy","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rabah A. Al-Zaidy","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004860693"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.5851,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75867238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9994999766349792,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9994999766349792,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7127155065536499},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6485772132873535},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5555998086929321},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.5443872213363647},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41950419545173645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3571198880672455},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34417325258255005},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3413536846637726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127155065536499},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6485772132873535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5555998086929321},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5443872213363647},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41950419545173645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3571198880672455},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34417325258255005},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3413536846637726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3103010.3121043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W89857650","https://openalex.org/W102708294","https://openalex.org/W1512387364","https://openalex.org/W1529533208","https://openalex.org/W1578697867","https://openalex.org/W2020082880","https://openalex.org/W2022166150","https://openalex.org/W2028657008","https://openalex.org/W2043622810","https://openalex.org/W2068737686","https://openalex.org/W2081580037","https://openalex.org/W2115461474","https://openalex.org/W2138605095","https://openalex.org/W2142086811","https://openalex.org/W2168065722","https://openalex.org/W2331870320","https://openalex.org/W2509019445","https://openalex.org/W2604887361"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2472885054","https://openalex.org/W2120460904","https://openalex.org/W1518289136","https://openalex.org/W2261602753","https://openalex.org/W4285194854","https://openalex.org/W4226095066"],"abstract_inverted_index":{"The":[0],"continuing":[1],"growth":[2],"of":[3,13,41,59,90],"published":[4],"scholarly":[5,42,141],"content":[6],"on":[7,38,163],"the":[8,11,14,80],"web":[9,115],"ensures":[10],"availability":[12],"most":[15,108],"recent":[16],"scientific":[17,128,156],"findings":[18],"to":[19,77,87,102,123,135,190],"researchers.":[20],"Scholarly":[21],"documents,":[22],"such":[23,97,105],"as":[24],"research":[25],"articles,":[26],"are":[27,36,100,112],"easily":[28],"accessed":[29],"by":[30],"using":[31],"academic":[32],"search":[33],"engines":[34],"that":[35,67,159,180],"built":[37,113],"large":[39,88,98],"repositories":[40,89],"documents.":[43,92,192],"Scientific":[44],"information":[45,64,157],"extraction":[46,65,158],"from":[47,114,140,186],"documents":[48,142],"into":[49],"a":[50,60,73,137,150,177],"structured":[51],"knowledge":[52,75,110,138,166],"graph":[53,139],"representation":[54],"facilitates":[55],"automated":[56],"machine":[57],"understanding":[58],"document's":[61],"content.":[62],"Traditional":[63],"approaches,":[66],"either":[68],"require":[69],"training":[70,94,171],"samples":[71],"or":[72],"preexisting":[74],"base":[76,167],"assist":[78],"in":[79,127],"extraction,":[81],"can":[82],"be":[83],"challenging":[84],"when":[85],"applied":[86],"digital":[91],"Labeled":[93],"examples":[95],"for":[96,104,155],"scale":[99],"difficult":[101],"obtain":[103],"datasets.":[106],"Also,":[107],"available":[109],"bases":[111],"data":[116],"and":[117,168,175],"do":[118],"not":[119,161],"have":[120],"sufficient":[121],"coverage":[122],"include":[124],"concepts":[125],"found":[126],"articles.":[129],"In":[130],"this":[131],"paper":[132],"we":[133],"aim":[134],"construct":[136],"while":[143],"addressing":[144],"both":[145],"these":[146],"issues.":[147],"We":[148,173],"propose":[149],"fully":[151],"automatic,":[152],"unsupervised":[153],"system":[154],"does":[160],"build":[162],"an":[164],"existing":[165],"avoids":[169],"manually-tagged":[170],"data.":[172],"describe":[174],"evaluate":[176],"constructed":[178],"taxonomy":[179],"contains":[181],"over":[182],"15k":[183],"entities":[184],"resulting":[185],"applying":[187],"our":[188],"approach":[189],"10k":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}