{"id":"https://openalex.org/W2757911951","doi":"https://doi.org/10.18653/v1/d17-1291","title":"Identifying Semantically Deviating Outlier Documents","display_name":"Identifying Semantically Deviating Outlier Documents","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2757911951","doi":"https://doi.org/10.18653/v1/d17-1291","mag":"2757911951"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1291","pdf_url":"https://www.aclweb.org/anthology/D17-1291.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1291.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011279860","display_name":"Honglei Zhuang","orcid":"https://orcid.org/0000-0001-8134-1509"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honglei Zhuang","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342213","display_name":"Chi Wang","orcid":"https://orcid.org/0000-0002-4751-8187"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chi Wang","raw_affiliation_strings":["Microsoft Research, Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043659320","display_name":"Fangbo Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangbo Tao","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022713560","display_name":"Lance Kaplan","orcid":"https://orcid.org/0000-0002-3627-4471"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lance Kaplan","raw_affiliation_strings":["US Army Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Lab","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2748","last_page":"2757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/outlier","display_name":"Outlier","score":0.8455169200897217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907205820083618},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5839389562606812},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5781795382499695},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5514770150184631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5461574196815491},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.538516104221344},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5203604102134705},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5154048204421997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4852468967437744},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.46559369564056396},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4324350655078888},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4196600317955017},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4115694761276245},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3260626792907715},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.256725549697876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07868045568466187}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8455169200897217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907205820083618},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5839389562606812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5781795382499695},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5514770150184631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461574196815491},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.538516104221344},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5203604102134705},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5154048204421997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4852468967437744},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.46559369564056396},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4324350655078888},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4196600317955017},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4115694761276245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3260626792907715},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.256725549697876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07868045568466187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1291","pdf_url":"https://www.aclweb.org/anthology/D17-1291.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1291","pdf_url":"https://www.aclweb.org/anthology/D17-1291.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G1346049954","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1898530342","display_name":"III: Small: Collaborative Research: Conflicts to Harmony: Integrating Massive Data by Trustworthiness Estimation and Truth Discovery","funder_award_id":"1320617","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3339524276","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3346663007","display_name":null,"funder_award_id":"grant 1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5190750194","display_name":null,"funder_award_id":"IIS-1320617, IIS 16-18481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5226638049","display_name":null,"funder_award_id":"Cooperative Agreement No. W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G6015371281","display_name":null,"funder_award_id":"No. W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G702127483","display_name":null,"funder_award_id":"IIS-1320617","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7561134949","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7903051118","display_name":null,"funder_award_id":"IIS 16-18481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G948678646","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2757911951.pdf","grobid_xml":"https://content.openalex.org/works/W2757911951.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W162256","https://openalex.org/W1981825277","https://openalex.org/W2022322548","https://openalex.org/W2099064293","https://openalex.org/W2117242598","https://openalex.org/W2120236791","https://openalex.org/W2122646361","https://openalex.org/W2131744502","https://openalex.org/W2137130182","https://openalex.org/W2150815390","https://openalex.org/W2151373442","https://openalex.org/W2153579005","https://openalex.org/W2169839551","https://openalex.org/W2250753706","https://openalex.org/W2336481247","https://openalex.org/W2964117810","https://openalex.org/W3208688400","https://openalex.org/W4231510805","https://openalex.org/W4241278037","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W2289741972","https://openalex.org/W2580878117","https://openalex.org/W4296501933","https://openalex.org/W3043161732","https://openalex.org/W3091147850","https://openalex.org/W2947963870","https://openalex.org/W2997152654","https://openalex.org/W2950634454"],"abstract_inverted_index":{"A":[0],"document":[1,5,21,48],"outlier":[2,118],"is":[3,82],"a":[4,16,51,56,77],"that":[6,98],"substantially":[7],"deviates":[8],"in":[9,15,26,50,66,87,110],"semantics":[10],"from":[11],"the":[12,42,67,73,117],"majority":[13],"ones":[14],"corpus.":[17,53],"Automatic":[18],"identification":[19],"of":[20,44,112,116],"outliers":[22,49],"can":[23,101],"be":[24],"valuable":[25],"many":[27],"applications,":[28],"such":[29],"as":[30],"screening":[31],"health":[32],"records":[33],"for":[34],"medical":[35],"mistakes.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"study":[41],"problem":[43],"mining":[45],"semantically":[46],"deviating":[47],"given":[52,74],"We":[54],"develop":[55],"generative":[57],"model":[58],"to":[59,71,84,105],"identify":[60],"frequent":[61],"and":[62,76],"characteristic":[63],"semantic":[64],"regions":[65],"word":[68],"embedding":[69],"space":[70],"represent":[72],"corpus,":[75],"robust":[78],"outlierness":[79],"measure":[80],"which":[81],"resistant":[83],"noisy":[85],"content":[86],"documents.":[88],"Experiments":[89],"conducted":[90],"on":[91],"two":[92],"real-world":[93],"textual":[94],"data":[95],"sets":[96],"show":[97],"our":[99],"method":[100],"achieve":[102],"an":[103],"up":[104],"135%":[106],"improvement":[107],"over":[108],"baselines":[109],"terms":[111],"recall":[113],"at":[114],"top-1%":[115],"ranking.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}