{"id":"https://openalex.org/W2105573333","doi":"https://doi.org/10.1145/1571941.1571946","title":"Refined experts","display_name":"Refined experts","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2105573333","doi":"https://doi.org/10.1145/1571941.1571946","mag":"2105573333"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1571946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","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/A5102869952","display_name":"Paul N. Bennett","orcid":"https://orcid.org/0000-0002-8846-5480"},"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":"Paul N. Bennett","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/A5101536309","display_name":"Nam Hoang Nguyen","orcid":"https://orcid.org/0000-0002-9476-3126"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Nguyen","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102869952"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":15.4012,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99082704,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9908000230789185,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.988099992275238,"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/mistake","display_name":"Mistake","score":0.791343092918396},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7394389510154724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341033220291138},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4698556661605835},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4515782594680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4515574872493744},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44857558608055115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44694092869758606},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.44122764468193054},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.41947656869888306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3595339059829712},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35628414154052734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1507754623889923},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13236114382743835}],"concepts":[{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.791343092918396},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7394389510154724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341033220291138},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4698556661605835},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4515782594680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4515574872493744},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44857558608055115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44694092869758606},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.44122764468193054},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.41947656869888306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3595339059829712},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35628414154052734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1507754623889923},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13236114382743835},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1571941.1571946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1523949738","https://openalex.org/W1549656520","https://openalex.org/W1553489951","https://openalex.org/W1618905105","https://openalex.org/W1620204465","https://openalex.org/W2005422315","https://openalex.org/W2008835805","https://openalex.org/W2014566476","https://openalex.org/W2023991263","https://openalex.org/W2025047573","https://openalex.org/W2025653905","https://openalex.org/W2059019405","https://openalex.org/W2063862666","https://openalex.org/W2073830447","https://openalex.org/W2091961126","https://openalex.org/W2105879985","https://openalex.org/W2106490775","https://openalex.org/W2117225622","https://openalex.org/W2117496083","https://openalex.org/W2121526711","https://openalex.org/W2122678284","https://openalex.org/W2125993116","https://openalex.org/W2126184790","https://openalex.org/W2142623206","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2912651257","https://openalex.org/W3015740509","https://openalex.org/W3042893949"],"related_works":["https://openalex.org/W1590719878","https://openalex.org/W4244271513","https://openalex.org/W2365974527","https://openalex.org/W4306382224","https://openalex.org/W4226517682","https://openalex.org/W3108263396","https://openalex.org/W2895872277","https://openalex.org/W1561425952","https://openalex.org/W2496555895","https://openalex.org/W4236454870"],"abstract_inverted_index":{"While":[0,78],"large-scale":[1],"taxonomies--especially":[2],"for":[3,9],"web":[4],"pages--have":[5],"been":[6],"in":[7,32,51,61,72,75,113,139],"existence":[8],"some":[10],"time,":[11],"approaches":[12],"to":[13,26,101,136],"automatically":[14],"classify":[15],"documents":[16],"into":[17],"these":[18],"taxonomies":[19],"have":[20],"met":[21],"with":[22],"limited":[23],"success":[24],"compared":[25],"the":[27,52,62,76,84,92,98,132],"more":[28],"general":[29],"progress":[30],"made":[31,59],"text":[33],"classification.":[34],"We":[35],"argue":[36],"that":[37,90,131],"this":[38],"stems":[39],"from":[40],"three":[41],"causes:":[42],"increasing":[43],"sparsity":[44],"of":[45],"training":[46,99],"data":[47],"at":[48],"deeper":[49],"nodes":[50,74],"taxonomy,":[53],"error":[54,103],"propagation":[55,104],"where":[56],"a":[57,114,119],"mistake":[58],"high":[60],"hierarchy":[63],"cannot":[64],"be":[65],"recovered,":[66],"and":[67,105],"increasingly":[68],"complex":[69],"decision":[70],"surfaces":[71],"higher":[73],"hierarchy.":[77],"prior":[79],"research":[80],"has":[81],"focused":[82],"on":[83],"first":[85],"problem,":[86],"we":[87,125],"introduce":[88],"methods":[89],"target":[91],"latter":[93],"two":[94],"problems--first":[95],"by":[96,107],"biasing":[97],"distribution":[100],"reduce":[102],"second":[106],"propagating":[108],"up":[109],"\"first-guess\"":[110],"expert":[111],"information":[112],"bottom-up":[115],"manner":[116],"before":[117],"making":[118],"refined":[120],"top":[121],"down":[122],"choice.":[123],"Finally,":[124],"present":[126],"an":[127,143],"empirical":[128],"study":[129],"demonstrating":[130],"suggested":[133],"changes":[134],"lead":[135],"10--30%":[137],"improvements":[138],"F1":[140],"scores":[141],"versus":[142],"accepted":[144],"competitive":[145],"baseline,":[146],"hierarchical":[147],"SVMs.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":15}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2016-06-24T00:00:00"}