{"id":"https://openalex.org/W2170934897","doi":"https://doi.org/10.1017/s1351324908004968","title":"Adapting SVM for data sparseness and imbalance: a case study in information extraction","display_name":"Adapting SVM for data sparseness and imbalance: a case study in information extraction","publication_year":2008,"publication_date":"2008-12-18","ids":{"openalex":"https://openalex.org/W2170934897","doi":"https://doi.org/10.1017/s1351324908004968","mag":"2170934897"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324908004968","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324908004968","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5009602058","display_name":"Yaoyong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"YAOYONG LI","raw_affiliation_strings":["Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021952588","display_name":"Kalina Bontcheva","orcid":"https://orcid.org/0000-0001-6152-9600"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"KALINA BONTCHEVA","raw_affiliation_strings":["Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000140583","display_name":"Hamish Cunningham","orcid":"https://orcid.org/0000-0001-5901-5483"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"HAMISH CUNNINGHAM","raw_affiliation_strings":["Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of SheffieldRegent Court, 211 Portobello, Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":13.0533,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.98471065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"2","first_page":"241","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9926000237464905,"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":0.8951153755187988},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7838833332061768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7635941505432129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7357729077339172},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6748999357223511},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4156155586242676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3239535689353943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8951153755187988},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7838833332061768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7635941505432129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7357729077339172},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6748999357223511},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4156155586242676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3239535689353943},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324908004968","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324908004968","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W138033052","https://openalex.org/W171478201","https://openalex.org/W174553219","https://openalex.org/W181643614","https://openalex.org/W200042785","https://openalex.org/W395877202","https://openalex.org/W1483816357","https://openalex.org/W1508165687","https://openalex.org/W1514940655","https://openalex.org/W1533960661","https://openalex.org/W1535936886","https://openalex.org/W1547701650","https://openalex.org/W1563088657","https://openalex.org/W1570871893","https://openalex.org/W1576520375","https://openalex.org/W1597941798","https://openalex.org/W1602152045","https://openalex.org/W1604938182","https://openalex.org/W1608462205","https://openalex.org/W1888943520","https://openalex.org/W1900116963","https://openalex.org/W1967350923","https://openalex.org/W1979495886","https://openalex.org/W1983073929","https://openalex.org/W1994485670","https://openalex.org/W1996087560","https://openalex.org/W1999595522","https://openalex.org/W2008074610","https://openalex.org/W2010588484","https://openalex.org/W2021372633","https://openalex.org/W2037866349","https://openalex.org/W2040909025","https://openalex.org/W2045993505","https://openalex.org/W2046319108","https://openalex.org/W2053238041","https://openalex.org/W2056451646","https://openalex.org/W2068541969","https://openalex.org/W2097388131","https://openalex.org/W2107008379","https://openalex.org/W2124583192","https://openalex.org/W2129665406","https://openalex.org/W2133864802","https://openalex.org/W2142114717","https://openalex.org/W2144578941","https://openalex.org/W2148603752","https://openalex.org/W2149430911","https://openalex.org/W2150102617","https://openalex.org/W2151239833","https://openalex.org/W2155925463","https://openalex.org/W2157791002","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2166496241","https://openalex.org/W2172000360","https://openalex.org/W2429914308","https://openalex.org/W2505930198","https://openalex.org/W2785717676","https://openalex.org/W3004533406","https://openalex.org/W3014813097","https://openalex.org/W3155649056","https://openalex.org/W4205896512","https://openalex.org/W4285719527","https://openalex.org/W6608051331","https://openalex.org/W6628964739","https://openalex.org/W6679426900","https://openalex.org/W6680007464","https://openalex.org/W6681325634","https://openalex.org/W6681875376","https://openalex.org/W6682953061"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W4206195464"],"abstract_inverted_index":{"Abstract":[0],"Support":[1],"Vector":[2],"Machines":[3],"(SVM)":[4],"have":[5],"been":[6],"used":[7,126],"successfully":[8],"in":[9,23,61,67,183,205],"many":[10],"Natural":[11],"Language":[12],"Processing":[13],"(NLP)":[14],"tasks.":[15,35],"The":[16,72],"novel":[17],"contribution":[18],"of":[19,51,131,186,209],"this":[20],"paper":[21],"is":[22,59],"investigating":[24],"two":[25,198],"techniques":[26,199],"for":[27,32,127,135,147,176,190,193],"making":[28],"SVM":[29,40,56,92,95],"more":[30],"suitable":[31],"language":[33],"learning":[34,58,107,133,188],"Firstly,":[36],"we":[37,109,139],"propose":[38],"an":[39],"with":[41,48,96,104,149,161],"uneven":[42],"margins":[43],"(SVMUM)":[44],"model":[45],"to":[46,63,157,180,202],"deal":[47],"the":[49,65,90,94,105,111,116,142,162,181,184,187,197],"problem":[50,189],"imbalanced":[52],"training":[53,70],"data.":[54,71],"Secondly,":[55],"active":[57,106],"employed":[60],"order":[62],"alleviate":[64],"difficulty":[66],"obtaining":[68],"labelled":[69],"algorithms":[73,134],"are":[74,122,167,173,200],"presented":[75],"and":[76,93,118,129,170,192],"evaluated":[77],"on":[78,115],"several":[79],"Information":[80],"Extraction":[81],"(IE)":[82],"tasks,":[83,196],"where":[84],"they":[85],"achieved":[86],"better":[87],"performance":[88],"than":[89],"standard":[91],"passive":[97],"learning,":[98],"respectively.":[99],"Moreover,":[100],"by":[101],"combining":[102],"SVMUM":[103],"algorithm,":[108],"achieve":[110],"best":[112],"reported":[113],"results":[114],"seminars":[117],"jobs":[119],"corpora,":[120],"which":[121,172],"benchmark":[123],"data":[124],"sets":[125],"evaluation":[128],"comparison":[130,156],"machine":[132],"IE.":[136],"In":[137,155],"addition,":[138],"also":[140],"evaluate":[141],"token":[143],"based":[144],"classification":[145],"framework":[146],"IE":[148,191],"three":[150],"different":[151],"entity":[152],"tagging":[153],"schemes.":[154],"previous":[158],"methods":[159,166],"dealing":[160],"same":[163],"problems,":[164],"our":[165],"both":[168],"effective":[169],"efficient,":[171],"valuable":[174],"features":[175],"real-world":[177],"applications.":[178],"Due":[179],"similarity":[182],"formulation":[185],"other":[194],"NLP":[195],"likely":[201],"be":[203],"beneficial":[204],"a":[206],"wide":[207],"range":[208],"applications":[210],"1":[211],".":[212]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}