{"id":"https://openalex.org/W3007933224","doi":"https://doi.org/10.1109/bigdata47090.2019.9005578","title":"Learning to Differentiate Between Main-articles and Sub-articles in Wikipedia","display_name":"Learning to Differentiate Between Main-articles and Sub-articles in Wikipedia","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007933224","doi":"https://doi.org/10.1109/bigdata47090.2019.9005578","mag":"3007933224"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9005578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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/A5102861481","display_name":"Muhao Chen","orcid":"https://orcid.org/0000-0003-0118-3147"},"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":"Muhao Chen","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031033543","display_name":"Changping Meng","orcid":"https://orcid.org/0009-0005-9427-6511"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changping Meng","raw_affiliation_strings":["Purdue University, West Lafayette"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101617703","display_name":"Gang Huang","orcid":"https://orcid.org/0000-0002-4686-3181"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Huang","raw_affiliation_strings":["Google Inc, Mountain View"],"affiliations":[{"raw_affiliation_string":"Google Inc, Mountain View","institution_ids":["https://openalex.org/I1291425158"]}]},{"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":["Department of Computer Science, University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102861481"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.3505,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74279572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1442","last_page":"1449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9918000102043152,"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/T13157","display_name":"Cancer-related gene regulation","score":0.9912999868392944,"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":0.7346370220184326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5626203417778015},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.531629204750061},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4093782901763916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346370220184326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5626203417778015},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.531629204750061},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4093782901763916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9005578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W1775434803","https://openalex.org/W1794039122","https://openalex.org/W1832693441","https://openalex.org/W1924770834","https://openalex.org/W1968969471","https://openalex.org/W2004763266","https://openalex.org/W2027041991","https://openalex.org/W2030109855","https://openalex.org/W2038880450","https://openalex.org/W2039438423","https://openalex.org/W2049434052","https://openalex.org/W2058236194","https://openalex.org/W2072128103","https://openalex.org/W2082674974","https://openalex.org/W2153579005","https://openalex.org/W2157311147","https://openalex.org/W2157331557","https://openalex.org/W2169053895","https://openalex.org/W2170738476","https://openalex.org/W2250966211","https://openalex.org/W2262787892","https://openalex.org/W2265846598","https://openalex.org/W2294860948","https://openalex.org/W2461871142","https://openalex.org/W2470673105","https://openalex.org/W2541518390","https://openalex.org/W2551361256","https://openalex.org/W2556888587","https://openalex.org/W2561529111","https://openalex.org/W2562439797","https://openalex.org/W2562607067","https://openalex.org/W2563010554","https://openalex.org/W2587972260","https://openalex.org/W2741805585","https://openalex.org/W2750927115","https://openalex.org/W2785523195","https://openalex.org/W2788596952","https://openalex.org/W2803119681","https://openalex.org/W2887976600","https://openalex.org/W2951359136","https://openalex.org/W2962916648","https://openalex.org/W2962958286","https://openalex.org/W2962985038","https://openalex.org/W2963911037","https://openalex.org/W2963918774","https://openalex.org/W2964207259","https://openalex.org/W2964263523","https://openalex.org/W2988167338","https://openalex.org/W3014179099","https://openalex.org/W4231109964","https://openalex.org/W4294170691","https://openalex.org/W6637845829","https://openalex.org/W6638444622","https://openalex.org/W6640212811","https://openalex.org/W6682691769","https://openalex.org/W6685160515","https://openalex.org/W6729331028","https://openalex.org/W6729752019","https://openalex.org/W6742554458","https://openalex.org/W6747620207","https://openalex.org/W6753648928"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Current":[0],"Wikipedia":[1,35,128],"editing":[2,69],"approaches":[3,70],"typically":[4],"summarize":[5],"a":[6,38,52,82,116,127,172,182],"named":[7],"entity":[8,112],"by":[9,13,98],"one":[10],"main-article":[11,101],"supplemented":[12],"multiple":[14],"sub-articles":[15,104],"describing":[16],"various":[17,205],"aspects":[18,160],"and":[19,59,73,78,144,154,158,179,187,201,203],"subtopics":[20],"of":[21,26,33,41,84,111,126,150,161,184],"the":[22,31,47,60,67,100,103,109,136,141,156,208],"entity.":[23],"Such":[24],"separation":[25],"articles":[27,61,197],"aims":[28],"at":[29,108],"improving":[30],"curation":[32],"content-rich":[34],"entities.":[36,65],"However,":[37],"wide":[39],"range":[40],"Wikipedia-based":[42],"technologies":[43],"critically":[44],"rely":[45],"on":[46,123,207],"article-as-concept":[48],"assumption,":[49],"which":[50],"requires":[51],"one-to-one":[53],"mapping":[54],"between":[55],"entities":[56],"(or":[57],"concepts)":[58],"that":[62,94,105,121],"describe":[63],"these":[64,96],"Thus,":[66],"current":[68],"sow":[71],"confusion":[72],"ambiguity":[74],"to":[75,81,170],"knowledge":[76],"representation,":[77],"cause":[79],"problems":[80,97],"wide-range":[83],"downstream":[85],"technologies.":[86],"In":[87,164],"this":[88,165],"paper,":[89],"we":[90,167],"present":[91],"an":[92],"approach":[93],"resolves":[95],"differentiating":[99],"from":[102,140],"are":[106],"not":[107],"core":[110],"representations.":[113],"We":[114],"propose":[115],"hybrid":[117],"neural":[118,132],"article":[119,142],"model":[120,192],"learns":[122],"two":[124],"facets":[125],"article:":[129],"(i)":[130],"Two":[131],"document":[133],"encoders":[134],"capture":[135],"latent":[137],"semantic":[138],"features":[139,152],"title":[143],"text":[145],"contents.":[146],"(ii)":[147],"A":[148],"set":[149],"explicit":[151],"measure":[153],"characterize":[155],"symbolic":[157],"structural":[159],"each":[162],"article.":[163],"study,":[166],"use":[168],"crowdsourcing":[169],"create":[171],"large":[173],"annotated":[174],"dataset":[175],"for":[176,180],"feature":[177],"extraction,":[178],"evaluating":[181],"variety":[183],"encoding":[185],"techniques":[186],"learning":[188],"structures.":[189],"The":[190],"optimized":[191],"so":[193],"derived":[194],"identifies":[195],"main":[196],"with":[198],"near-perfect":[199],"precision":[200],"recall,":[202],"outperforms":[204],"baselines":[206],"contributed":[209],"dataset.":[210]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}