{"id":"https://openalex.org/W2055637601","doi":"https://doi.org/10.1017/s1351324904003559","title":"Machine learning-based named entity recognition via effective integration of various evidences","display_name":"Machine learning-based named entity recognition via effective integration of various evidences","publication_year":2005,"publication_date":"2005-05-19","ids":{"openalex":"https://openalex.org/W2055637601","doi":"https://doi.org/10.1017/s1351324904003559","mag":"2055637601"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324904003559","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324904003559","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/A5012794465","display_name":"Guodong Zhou","orcid":"https://orcid.org/0000-0002-7887-5099"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"GUODONG ZHOU","raw_affiliation_strings":["Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail:","Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail: zhougd@i2r.a-star.edu.sg, sujian@i2r.a-star.edu.sg"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail:","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail: zhougd@i2r.a-star.edu.sg, sujian@i2r.a-star.edu.sg","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101860993","display_name":"Jian Su","orcid":"https://orcid.org/0009-0001-9484-5885"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"JIAN SU","raw_affiliation_strings":["Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail:","Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail: zhougd@i2r.a-star.edu.sg, sujian@i2r.a-star.edu.sg"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail:","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, 21 Heng Mui Keng Terrace Singapore 119613 e-mail: zhougd@i2r.a-star.edu.sg, sujian@i2r.a-star.edu.sg","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012794465"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.8775,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80186342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"11","issue":"2","first_page":"189","last_page":"206"},"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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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":0.8744250535964966},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7272723317146301},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6169356107711792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.598054051399231},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5956956148147583},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5512467622756958},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5239869952201843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5194144248962402},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4527471661567688},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44666606187820435},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.28067106008529663},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.12067347764968872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744250535964966},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7272723317146301},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6169356107711792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.598054051399231},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5956956148147583},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5512467622756958},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5239869952201843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5194144248962402},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4527471661567688},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44666606187820435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28067106008529663},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.12067347764968872},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324904003559","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324904003559","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":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W14030242","https://openalex.org/W24163152","https://openalex.org/W89503205","https://openalex.org/W163474282","https://openalex.org/W1505083828","https://openalex.org/W1520377376","https://openalex.org/W1568095077","https://openalex.org/W1568620938","https://openalex.org/W1606142945","https://openalex.org/W1941319617","https://openalex.org/W1971763646","https://openalex.org/W1982982698","https://openalex.org/W1991133427","https://openalex.org/W2033209333","https://openalex.org/W2039276255","https://openalex.org/W2045993505","https://openalex.org/W2051721519","https://openalex.org/W2088970556","https://openalex.org/W2098921539","https://openalex.org/W2117400858","https://openalex.org/W2123512824","https://openalex.org/W2125838338","https://openalex.org/W2131010894","https://openalex.org/W2134237567"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W3000685722","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W2520117834","https://openalex.org/W2883921205","https://openalex.org/W4313162113","https://openalex.org/W1884363728","https://openalex.org/W3133906981"],"abstract_inverted_index":{"Named":[0],"entity":[1,6,55,92,160,195],"recognition":[2,161],"identifies":[3],"and":[4,21,28,36,50,65,84,88,111,141,185,191,197,204,230,259],"classifies":[5],"names":[7],"in":[8,25,39,136],"a":[9,45,52,100,217,231],"text":[10],"document":[11],"into":[12],"some":[13],"predefined":[14],"categories.":[15],"It":[16],"resolves":[17],"the":[18,31,34,59,63,74,106,119,129,132,137,151,158,171,182,189,200,209,225,239,251],"\u201cwho\u201d,":[19],"\u201cwhere\u201d":[20],"\u201chow":[22],"much\u201d":[23],"problems":[24,38],"information":[26],"extraction":[27],"leads":[29],"to":[30,71,81],"resolution":[32],"of":[33,91,105,118,131,188,202,224,238],"\u201cwhat\u201d":[35],"\u201chow\u201d":[37],"further":[40],"processing.":[41],"This":[42],"paper":[43],"presents":[44],"Hidden":[46],"Markov":[47],"Model":[48],"(HMM)":[49],"proposes":[51],"HMM-based":[53],"named":[54,159,194],"recognizer":[56],"implemented":[57],"as":[58,109],"system":[60],"PowerNE.":[61],"Through":[62],"HMM":[64],"an":[66,114,123,143],"effective":[67],"constraint":[68],"relaxation":[69],"algorithm":[70],"deal":[72],"with":[73,150,170,208,221,235],"data":[75,187,227,241],"sparseness":[76],"problem,":[77],"PowerNE":[78,166],"is":[79,163],"able":[80],"effectively":[82],"apply":[83],"integrate":[85],"various":[86],"internal":[87,103,115,124],"external":[89,144],"evidences":[90,96],"names.":[93],"Currently,":[94],"four":[95],"are":[97],"included:":[98],"(1)":[99],"simple":[101],"deterministic":[102],"feature":[104,117],"words,":[107],"such":[108],"capitalization":[110],"digitalization;":[112],"(2)":[113],"semantic":[116],"important":[120],"triggers;":[121],"(3)":[122],"gazetteer":[125,139],"feature,":[126,147],"which":[127,148],"determines":[128],"appearance":[130],"current":[133],"word":[134],"string":[135],"provided":[138],"list;":[140],"(4)":[142],"macro":[145],"context":[146],"deals":[149],"name":[152],"alias":[153],"phenomena.":[154],"In":[155,244],"this":[156],"way,":[157],"problem":[162],"resolved":[164],"effectively.":[165],"has":[167],"been":[168],"benchmarked":[169],"Message":[172],"Understanding":[173],"Conferences":[174],"(MUC)":[175],"data.":[176],"The":[177],"evaluation":[178],"shows":[179],"that,":[180],"using":[181],"formal":[183],"training":[184,226,240],"test":[186],"MUC-6":[190,258],"MUC-7":[192],"English":[193],"tasks,":[196],"it":[198,215,246],"achieves":[199,216],"F-measures":[201],"96.6":[203],"94.1,":[205],"respectively.":[206],"Compared":[207],"best":[210,252],"reported":[211,253],"machine":[212],"learning":[213],"system,":[214],"1.7":[218],"higher":[219,233],"F-measure":[220,234],"one":[222,236],"quarter":[223],"on":[228,242,257],"MUC-6,":[229],"3.6":[232],"ninth":[237],"MUC-7.":[243,260],"addition,":[245],"performs":[247],"slightly":[248],"better":[249],"than":[250],"handcrafted":[254],"rule-based":[255],"systems":[256]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}