{"id":"https://openalex.org/W2154210598","doi":"https://doi.org/10.1162/089120101750300508","title":"Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems","display_name":"Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems","publication_year":2001,"publication_date":"2001-06-01","ids":{"openalex":"https://openalex.org/W2154210598","doi":"https://doi.org/10.1162/089120101750300508","mag":"2154210598"},"language":"en","primary_location":{"id":"doi:10.1162/089120101750300508","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089120101750300508","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5078496738","display_name":"Hans van Halteren","orcid":"https://orcid.org/0000-0001-8115-1799"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hans van Halteren","raw_affiliation_strings":["TOSCA/Language & Speech, University of Nijmegen, P.O. Box 9103, 6500 HD Nijmegen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TOSCA/Language & Speech, University of Nijmegen, P.O. Box 9103, 6500 HD Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070643074","display_name":"Jakub Zavrel","orcid":null},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jakub Zavrel","raw_affiliation_strings":["Textkernel BV, University of Antwerp, Universiteitsplein 1, 2610 Wilrijk, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Textkernel BV, University of Antwerp, Universiteitsplein 1, 2610 Wilrijk, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Walter Daelemans","raw_affiliation_strings":["CNTS/Language Technology Group, University of Antwerp, Universiteitsplein 1, 2610 Wilrijk, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNTS/Language Technology Group, University of Antwerp, Universiteitsplein 1, 2610 Wilrijk, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.2075,"has_fulltext":false,"cited_by_count":186,"citation_normalized_percentile":{"value":0.9940842,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"2","first_page":"199","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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":0.9991000294685364,"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":0.9865999817848206,"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":0.8755165934562683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7362600564956665},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6687036752700806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6318877935409546},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.6079800724983215},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.563651442527771},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5444005131721497},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5176437497138977},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4710797071456909},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.45517590641975403},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4424339532852173},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4334034025669098},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41874057054519653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3492986261844635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755165934562683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7362600564956665},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6687036752700806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6318877935409546},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.6079800724983215},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.563651442527771},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5444005131721497},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5176437497138977},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4710797071456909},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.45517590641975403},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4424339532852173},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4334034025669098},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41874057054519653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3492986261844635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/089120101750300508","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089120101750300508","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:c:irua:33156","is_oa":false,"landing_page_url":"https://hdl.handle.net/10067/331560151162165141","pdf_url":null,"source":{"id":"https://openalex.org/S4377196495","display_name":"Anet (University of Antwerp)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149213910","host_organization_name":"University of Antwerp","host_organization_lineage":["https://openalex.org/I149213910"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:acl.sr.language-archives.org:J01-2002","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/J01-2002","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:doaj.org/article:6c1f9397bdbc41b4858472dc2a8f391e","is_oa":false,"landing_page_url":"https://doaj.org/article/6c1f9397bdbc41b4858472dc2a8f391e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 27, Iss 2 (2021)","raw_type":"article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/205453","is_oa":false,"landing_page_url":"http://hdl.handle.net/2066/205453","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, 27, 2, pp. 199-229","raw_type":"Article / Letter to editor"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W121755497","https://openalex.org/W196071926","https://openalex.org/W1494812392","https://openalex.org/W1496929357","https://openalex.org/W1502112145","https://openalex.org/W1507680813","https://openalex.org/W1529196404","https://openalex.org/W1541752891","https://openalex.org/W1551773846","https://openalex.org/W1571096757","https://openalex.org/W1582036668","https://openalex.org/W1586887050","https://openalex.org/W1597379537","https://openalex.org/W1632114991","https://openalex.org/W1676820704","https://openalex.org/W1773803948","https://openalex.org/W1781980207","https://openalex.org/W1812115632","https://openalex.org/W1969482724","https://openalex.org/W1975879310","https://openalex.org/W1986363862","https://openalex.org/W1994851566","https://openalex.org/W2036289382","https://openalex.org/W2040424159","https://openalex.org/W2042614373","https://openalex.org/W2061271742","https://openalex.org/W2081687495","https://openalex.org/W2096175520","https://openalex.org/W2112076978","https://openalex.org/W2118996379","https://openalex.org/W2119468407","https://openalex.org/W2125055259","https://openalex.org/W2129675461","https://openalex.org/W2130636661","https://openalex.org/W2135843243","https://openalex.org/W2136717444","https://openalex.org/W2143773250","https://openalex.org/W2150827725","https://openalex.org/W2167277498","https://openalex.org/W2170381724","https://openalex.org/W2215155232","https://openalex.org/W2249186037","https://openalex.org/W2333790164","https://openalex.org/W2599871100","https://openalex.org/W2912934387","https://openalex.org/W2914176692","https://openalex.org/W2914369697","https://openalex.org/W3041853209","https://openalex.org/W3087923659","https://openalex.org/W4205167092","https://openalex.org/W4212883601","https://openalex.org/W4231741839","https://openalex.org/W4240294902","https://openalex.org/W4241348453","https://openalex.org/W4242746271"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W1965453504","https://openalex.org/W2594897229","https://openalex.org/W2128096361","https://openalex.org/W2363447991","https://openalex.org/W3022465890","https://openalex.org/W2349070910","https://openalex.org/W2786860311","https://openalex.org/W2461981617"],"abstract_inverted_index":{"We":[0,30],"examine":[1],"how":[2],"differences":[3],"in":[4,95,102],"language":[5],"models,":[6],"learned":[7],"by":[8,33],"different":[9,50],"data-driven":[10],"systems":[11],"performing":[12],"the":[13,26,38,46,69,100,112],"same":[14,70],"NLP":[15],"task,":[16],"can":[17,105],"be":[18,106],"exploited":[19],"to":[20],"yield":[21],"a":[22],"higher":[23],"accuracy":[24],"than":[25],"best":[27,91],"individual":[28],"system.":[29],"do":[31],"this":[32],"means":[34],"of":[35,40,48],"experiments":[36],"involving":[37],"task":[39],"morphosyntactic":[41],"word":[42],"class":[43],"tagging,":[44],"on":[45,68],"basis":[47],"three":[49],"tagged":[51],"corpora.":[52],"Four":[53],"well-known":[54],"tagger":[55],"generators":[56],"(hidden":[57],"Markov":[58],"model,":[59],"memory-based,":[60],"transformation":[61],"rules,":[62],"and":[63,83],"maximum":[64],"entropy)":[65],"are":[66,77],"trained":[67],"corpus":[71],"data.":[72],"After":[73],"comparison,":[74],"their":[75,90],"outputs":[76],"combined":[78],"using":[79],"several":[80],"voting":[81],"strategies":[82],"second-stage":[84],"classifiers.":[85],"All":[86],"combination":[87],"taggers":[88],"outperform":[89],"component.":[92],"The":[93],"reduction":[94],"error":[96],"rate":[97],"varies":[98],"with":[99,111],"material":[101],"question,":[103],"but":[104],"as":[107,109],"high":[108],"24.3%":[110],"LOB":[113],"corpus.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}