{"id":"https://openalex.org/W2036956884","doi":"https://doi.org/10.1145/2566486.2568013","title":"Effective named entity recognition for idiosyncratic web collections","display_name":"Effective named entity recognition for idiosyncratic web collections","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W2036956884","doi":"https://doi.org/10.1145/2566486.2568013","mag":"2036956884"},"language":"en","primary_location":{"id":"doi:10.1145/2566486.2568013","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2566486.2568013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on World wide web","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/A5031803415","display_name":"Roman Prokofyev","orcid":null},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Roman Prokofyev","raw_affiliation_strings":["University of Fribourg, Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052565959","display_name":"Gianluca Demartini","orcid":"https://orcid.org/0000-0002-7311-3693"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gianluca Demartini","raw_affiliation_strings":["University of Fribourg, Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028454093","display_name":"Philippe Cudr\u00e9-Mauroux","orcid":"https://orcid.org/0000-0003-2588-4212"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philippe Cudr\u00e9-Mauroux","raw_affiliation_strings":["University of Fribourg, Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031803415"],"corresponding_institution_ids":["https://openalex.org/I154338468"],"apc_list":null,"apc_paid":null,"fwci":6.7522,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96743726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"397","last_page":"408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.8441402912139893},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7558892369270325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6534826755523682},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6096805334091187},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5897142887115479},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49680522084236145},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4694891571998596},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42151764035224915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4170266389846802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.408670574426651},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.32187619805336},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09056246280670166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441402912139893},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7558892369270325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6534826755523682},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6096805334091187},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5897142887115479},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49680522084236145},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4694891571998596},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42151764035224915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4170266389846802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.408670574426651},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.32187619805336},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09056246280670166},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2566486.2568013","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2566486.2568013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.938.9558","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.938.9558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wwwconference.org/proceedings/www2014/proceedings/p397.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.939.7170","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.939.7170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Philippe_Cudre-Mauroux/publication/261959866_Effective_named_entity_recognition_for_idiosyncratic_web_collections/links/0deec5363883726731000000.pdf","raw_type":"text"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:6d882b2","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G7959903129","display_name":null,"funder_award_id":"PP00P2 128459","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W12821309","https://openalex.org/W1502994231","https://openalex.org/W1515435652","https://openalex.org/W1529731474","https://openalex.org/W1532325895","https://openalex.org/W1575332430","https://openalex.org/W1773803948","https://openalex.org/W1907578970","https://openalex.org/W1976339715","https://openalex.org/W1997189720","https://openalex.org/W1998284155","https://openalex.org/W2001792610","https://openalex.org/W2004763266","https://openalex.org/W2009591769","https://openalex.org/W2046240631","https://openalex.org/W2049107599","https://openalex.org/W2056132907","https://openalex.org/W2067879405","https://openalex.org/W2081580037","https://openalex.org/W2083214110","https://openalex.org/W2096765155","https://openalex.org/W2097385711","https://openalex.org/W2097807612","https://openalex.org/W2100341149","https://openalex.org/W2101234009","https://openalex.org/W2113878109","https://openalex.org/W2131357087","https://openalex.org/W2145766604","https://openalex.org/W2168044903","https://openalex.org/W2169918010","https://openalex.org/W2171450492","https://openalex.org/W2531563875","https://openalex.org/W2565319307","https://openalex.org/W2607303097","https://openalex.org/W2804824276","https://openalex.org/W2997591727"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W3000685722","https://openalex.org/W2593907245","https://openalex.org/W2520117834","https://openalex.org/W4313162113","https://openalex.org/W1884363728","https://openalex.org/W3133906981","https://openalex.org/W4253099099"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recognition":[2],"(NER)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,54],"a":[9,142,161],"variety":[10],"of":[11,108,127,144,164],"online":[12],"information":[13],"management":[14],"tasks":[15],"including":[16],"text":[17],"categorization,":[18],"document":[19,68],"clustering,":[20],"and":[21,43,78,82,96,147,150,178],"faceted":[22],"search.":[23],"While":[24],"recent":[25],"NER":[26,65,128,173],"systems":[27],"can":[28,120],"achieve":[29],"near-human":[30],"performance":[31],"on":[32,66,75,136,187],"certain":[33],"documents":[34],"like":[35,114,118],"news":[36],"articles,":[37],"they":[38],"still":[39],"remain":[40],"highly":[41],"domain-specific":[42],"thus":[44],"cannot":[45],"effectively":[46],"identify":[47],"entities":[48],"such":[49,183],"as":[50,71,184],"original":[51],"technical":[52],"concepts":[53],"scientific":[55,72,176],"documents.":[56],"In":[57,101],"this":[58],"work,":[59],"we":[60,103,167],"propose":[61,168],"novel":[62],"approaches":[63,182],"for":[64,129],"distinctive":[67],"collections":[69,139,177],"(such":[70],"articles)":[73],"based":[74,186],"n-grams":[76],"inspection":[77],"classification.":[79],"We":[80,132],"design":[81],"evaluate":[83,133],"several":[84],"entity":[85],"recognition":[86],"features---ranging":[87],"from":[88,141],"well-known":[89],"part-of-speech":[90],"tags":[91],"to":[92,123,171],"n-gram":[93],"co-location":[94],"statistics":[95],"decision":[97],"trees---to":[98],"classify":[99],"candidates.":[100],"addition,":[102],"show":[104,159],"how":[105],"the":[106,125,165],"use":[107],"external":[109],"knowledge":[110],"bases":[111],"(either":[112],"specific":[113],"DBLP":[115],"or":[116],"generic":[117],"DBPedia)":[119],"be":[121],"leveraged":[122],"improve":[124],"effectiveness":[126],"idiosyncratic":[130],"collections.":[131],"our":[134],"system":[135],"two":[137],"test":[138],"created":[140],"set":[143],"Computer":[145],"Science":[146],"Physics":[148],"papers":[149],"compare":[151],"it":[152],"against":[153],"state-of-the-art":[154,181],"supervised":[155],"methods.":[156],"Experimental":[157],"results":[158],"that":[160],"careful":[162],"combination":[163],"features":[166],"yield":[169],"up":[170],"85%":[172],"accuracy":[174],"over":[175],"substantially":[179],"outperforms":[180],"those":[185],"maximum":[188],"entropy.":[189]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}