{"id":"https://openalex.org/W2096820050","doi":"https://doi.org/10.1145/1401890.1401927","title":"Entity categorization over large document collections","display_name":"Entity categorization over large document collections","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2096820050","doi":"https://doi.org/10.1145/1401890.1401927","mag":"2096820050"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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":null,"display_name":"Venkatesh Ganti","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Venkatesh Ganti","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034735876","display_name":"Arnd Christian K\u00f6nig","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnd C. K\u00f6nig","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007859752","display_name":"Rares Vernica","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rares Vernica","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.6919,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94563599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973000288009644,"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":0.8795208930969238},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8137989044189453},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7050319314002991},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6801716089248657},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6775492429733276},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.669657289981842},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5651271939277649},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5087354779243469},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4335169792175293},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4329376518726349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.359477698802948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27508658170700073},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18365082144737244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8795208930969238},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8137989044189453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7050319314002991},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6801716089248657},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6775492429733276},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.669657289981842},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5651271939277649},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5087354779243469},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4335169792175293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4329376518726349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.359477698802948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27508658170700073},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18365082144737244},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1401890.1401927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.613","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Ervernica/pub/kdd08-p274-ganti.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.869.7610","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.869.7610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/74047/rtp404-konig.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W57058802","https://openalex.org/W119080155","https://openalex.org/W157725869","https://openalex.org/W165944615","https://openalex.org/W167149422","https://openalex.org/W1493490255","https://openalex.org/W1510676953","https://openalex.org/W1515839227","https://openalex.org/W2008547014","https://openalex.org/W2071305045","https://openalex.org/W2080234606","https://openalex.org/W2096891167","https://openalex.org/W2103224511","https://openalex.org/W2119281377","https://openalex.org/W2123512824","https://openalex.org/W2123845384","https://openalex.org/W2130706307","https://openalex.org/W2141099517","https://openalex.org/W2154148563","https://openalex.org/W2158237121","https://openalex.org/W2159491434","https://openalex.org/W2166900514","https://openalex.org/W2167973519","https://openalex.org/W6604749631","https://openalex.org/W6629638141"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Extracting":[0],"entities":[1,56,88,105,119],"(such":[2,12],"as":[3,13],"people,":[4],"movies)":[5],"from":[6],"documents":[7,77,112],"and":[8,22,80,113,147],"identifying":[9],"the":[10,35,50,64,102,115,143,148],"categories":[11],"painter,":[14],"writer)":[15],"they":[16],"belong":[17],"to":[18,107,127],"enable":[19],"structured":[20],"querying":[21],"data":[23,139],"analysis":[24],"over":[25],"unstructured":[26],"document":[27,52],"collections.":[28],"In":[29,58],"this":[30,46,59],"paper,":[31,60],"we":[32,61],"focus":[33],"on":[34,137],"problem":[36],"of":[37,66,86,91,104,117,150],"categorizing":[38],"extracted":[39],"entities.":[40],"Most":[41],"prior":[42],"approaches":[43,96],"developed":[44],"for":[45],"task":[47],"only":[48],"analyzed":[49],"local":[51],"context":[53,74,103],"within":[54],"which":[55],"occur.":[57],"significantly":[62],"improve":[63],"accuracy":[65,146],"entity":[67],"categorization":[68],"by":[69],"(i)":[70],"considering":[71],"an":[72],"entity's":[73],"across":[75,110],"multiple":[76],"containing":[78],"it,":[79],"(ii)":[81],"exploiting":[82],"existing":[83],"large":[84],"lists":[85,90,116],"related":[87,118],"(e.g.,":[89],"actors,":[92],"directors,":[93],"books).":[94],"These":[95],"introduce":[97],"computational":[98],"challenges":[99],"because":[100],"(a)":[101],"has":[106],"be":[108,121],"aggregated":[109],"several":[111],"(b)":[114],"may":[120],"very":[122],"large.":[123],"We":[124,131],"develop":[125],"techniques":[126],"address":[128],"these":[129],"challenges.":[130],"present":[132],"a":[133],"thorough":[134],"experimental":[135],"study":[136],"real":[138],"sets":[140],"that":[141],"demonstrates":[142],"increase":[144],"in":[145],"scalability":[149],"our":[151],"approaches.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}