{"id":"https://openalex.org/W2010081016","doi":"https://doi.org/10.1145/2694428.2694437","title":"Text-Mining, Structured Queries, and Knowledge Management on Web Document Corpora","display_name":"Text-Mining, Structured Queries, and Knowledge Management on Web Document Corpora","publication_year":2014,"publication_date":"2014-12-04","ids":{"openalex":"https://openalex.org/W2010081016","doi":"https://doi.org/10.1145/2694428.2694437","mag":"2010081016"},"language":"en","primary_location":{"id":"doi:10.1145/2694428.2694437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2694428.2694437","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-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/A5103068308","display_name":"Hamid Mousavi","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hamid Mousavi","raw_affiliation_strings":["CSD, UCLA, Los Angeles, CA","CSD, UCLA, Los Angeles, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA","institution_ids":[]},{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088120071","display_name":"Maurizio Atzori","orcid":"https://orcid.org/0000-0001-6112-7310"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maurizio Atzori","raw_affiliation_strings":["University of Cagliari, Cagliari, Italy"],"affiliations":[{"raw_affiliation_string":"University of Cagliari, Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109033870","display_name":"Shi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi Gao","raw_affiliation_strings":["CSD, UCLA, Los Angeles, CA","CSD, UCLA, Los Angeles, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA","institution_ids":[]},{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113467760","display_name":"Carlo Zaniolo","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlo Zaniolo","raw_affiliation_strings":["CSD, UCLA, Los Angeles, CA","CSD, UCLA, Los Angeles, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA","institution_ids":[]},{"raw_affiliation_string":"CSD, UCLA, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103068308"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.1143,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89305887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"43","issue":"3","first_page":"48","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9984999895095825,"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":0.9973999857902527,"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":0.910892903804779},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.7927762269973755},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6815049052238464},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.602469801902771},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.47064560651779175},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4674806296825409},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42857202887535095},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.410581111907959},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.3312980532646179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.910892903804779},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.7927762269973755},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6815049052238464},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.602469801902771},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.47064560651779175},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4674806296825409},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42857202887535095},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.410581111907959},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3312980532646179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2694428.2694437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2694428.2694437","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.687.1009","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.687.1009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/publications/sigmod-record/1409/pdfs/07.systems-Mousavi.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unica.it:11584/57990","is_oa":false,"landing_page_url":"http://hdl.handle.net/11584/57990","pdf_url":null,"source":{"id":"https://openalex.org/S4377196293","display_name":"UNICA IRIS Institutional Research Information System (University of Cagliari)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172446870","host_organization_name":"University of Cagliari","host_organization_lineage":["https://openalex.org/I172446870"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W344601009","https://openalex.org/W1509982784","https://openalex.org/W1512387364","https://openalex.org/W1965998605","https://openalex.org/W1990119545","https://openalex.org/W2011992920","https://openalex.org/W2038721957","https://openalex.org/W2071247581","https://openalex.org/W2091301598","https://openalex.org/W2094728533","https://openalex.org/W2107901333","https://openalex.org/W2122865749","https://openalex.org/W2138605095","https://openalex.org/W2149468406","https://openalex.org/W2153225416","https://openalex.org/W2160009115"],"related_works":["https://openalex.org/W1541691357","https://openalex.org/W2090135255","https://openalex.org/W2168409722","https://openalex.org/W2782437235","https://openalex.org/W4387163706","https://openalex.org/W2548972888","https://openalex.org/W2026505290","https://openalex.org/W1993715838","https://openalex.org/W2085965157","https://openalex.org/W2359088421"],"abstract_inverted_index":{"Wikipedia's":[0],"InfoBoxes":[1],"play":[2],"a":[3,90,103,111],"crucial":[4],"role":[5],"in":[6,159],"advanced":[7],"applications":[8],"and":[9,17,41,78,81,84,95,123,137,152],"provide":[10,89],"the":[11,18,51,63,68,97,119,133,140,150,156,160,165],"main":[12],"knowledge":[13,98,134,161,170],"source":[14],"for":[15,31,93,132,155],"DBpedia":[16],"powerful":[19],"structured":[20,144],"queries":[21,145],"it":[22],"supports.":[23],"However,":[24],"InfoBoxes,":[25],"which":[26,118],"were":[27],"created":[28],"by":[29,58,71,148],"crowdsourcing":[30],"human":[32],"rather":[33],"than":[34],"computer":[35],"consumption,":[36],"suffer":[37],"from":[38,109,117],"incompleteness,":[39],"inconsistencies,":[40],"inaccuracies.":[42],"To":[43],"overcome":[44],"these":[45],"problems,":[46],"we":[47],"have":[48],"developed":[49],"(i)":[50],"IBminer":[52,72,101],"system":[53,65,120],"that":[54,66,74,88],"extracts":[55],"InfoBox":[56,85],"information":[57,69,157],"text-mining":[59],"Wikipedia":[60],"pages,":[61],"(ii)":[62],"IKBStore":[64,136],"integrates":[67],"derived":[70],"with":[73,164],"of":[75,146,167],"DBpedia,":[76],"YAGO2,WikiData,WordNet,":[77],"other":[79],"sources,":[80],"(iii)":[82],"SWiPE":[83,147],"Editor":[86],"(IBE)":[87],"user-friendly":[91],"interfaces":[92],"querying":[94],"revising":[96],"base.":[99,135],"Thus,":[100],"uses":[102],"deep":[104],"NLP-based":[105],"approach":[106],"to":[107],"extract":[108],"text":[110],"semantic":[112],"representation":[113],"structure":[114],"called":[115],"TextGraph":[116],"detects":[121],"patterns":[122],"derives":[124],"subject-attribute-value":[125],"relations,":[126],"as":[127,129],"well":[128],"domain-specific":[130],"synonyms":[131],"IBE":[138],"complement":[139],"powerful,":[141],"user-friendly,":[142],"by-example":[143],"supporting":[149],"validation":[151],"provenance":[153],"history":[154],"contained":[158],"base,":[162],"along":[163],"ability":[166],"upgrading":[168],"its":[169],"when":[171],"this":[172],"is":[173],"found":[174],"incomplete,":[175],"incorrect,":[176],"or":[177],"outdated.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
