{"id":"https://openalex.org/W2161629790","doi":"https://doi.org/10.1142/s0218213009000147","title":"COMBINING TEXT CLASSIFIERS AND HIDDEN MARKOV MODELS FOR INFORMATION EXTRACTION","display_name":"COMBINING TEXT CLASSIFIERS AND HIDDEN MARKOV MODELS FOR INFORMATION EXTRACTION","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2161629790","doi":"https://doi.org/10.1142/s0218213009000147","mag":"2161629790"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213009000147","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213009000147","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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/A5101191519","display_name":"Fl\u00e1via A. Barros","orcid":null},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"FL\u00c1VIA A. BARROS","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021117504","display_name":"Eduardo F. A. Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"EDUARDO F. A. SILVA","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083998049","display_name":"Ricardo B. C. Prud\u00eancio","orcid":"https://orcid.org/0000-0001-7084-1233"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"RICARDO B. C. PRUD\u00caNCIO","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043459746","display_name":"Valmir M. Filho","orcid":null},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"VALMIR M. FILHO","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074948157","display_name":"Andr\u00e9 Nascimento","orcid":"https://orcid.org/0000-0002-9333-3212"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"ANDR\u00c9 C. A. NASCIMENTO","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Pobox 7851 \u2013 CEP 50732-970 \u2013 Recife (PE), Brazil","institution_ids":["https://openalex.org/I25112270"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25112270"],"apc_list":null,"apc_paid":null,"fwci":0.7767,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84799674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"18","issue":"02","first_page":"311","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9973999857902527,"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":0.9965000152587891,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8889926671981812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8847426176071167},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6467812061309814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329718828201294},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5716477632522583},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5135176777839661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5082995295524597},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49971795082092285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44121119379997253},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.4296506643295288},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.39868420362472534},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.37385037541389465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3564702868461609},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.1890520453453064}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8889926671981812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8847426176071167},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6467812061309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329718828201294},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5716477632522583},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5135176777839661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5082995295524597},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49971795082092285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44121119379997253},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.4296506643295288},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.39868420362472534},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.37385037541389465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3564702868461609},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.1890520453453064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213009000147","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213009000147","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W65621272","https://openalex.org/W167149422","https://openalex.org/W200042785","https://openalex.org/W335893752","https://openalex.org/W1502749598","https://openalex.org/W1528113134","https://openalex.org/W1529355025","https://openalex.org/W1554892943","https://openalex.org/W1568339100","https://openalex.org/W1584713052","https://openalex.org/W1660390307","https://openalex.org/W1667964228","https://openalex.org/W1732623802","https://openalex.org/W1837359179","https://openalex.org/W1912123407","https://openalex.org/W1985789779","https://openalex.org/W1994485670","https://openalex.org/W1999595522","https://openalex.org/W2029873015","https://openalex.org/W2056760935","https://openalex.org/W2065568440","https://openalex.org/W2099196804","https://openalex.org/W2105395040","https://openalex.org/W2105594594","https://openalex.org/W2125035899","https://openalex.org/W2134150392","https://openalex.org/W2136867873","https://openalex.org/W2141408223","https://openalex.org/W2143349571","https://openalex.org/W2147169507","https://openalex.org/W2147880316","https://openalex.org/W2149430911","https://openalex.org/W2154444297","https://openalex.org/W2160758783","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2171332245"],"related_works":["https://openalex.org/W2134386692","https://openalex.org/W2379938888","https://openalex.org/W1510894296","https://openalex.org/W2116722627","https://openalex.org/W1977445474","https://openalex.org/W4233405330","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2799426416","https://openalex.org/W4246505579"],"abstract_inverted_index":{"In":[0,68,97],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,28,40,57,85,91,110,116],"hybrid":[6],"machine":[7],"learning":[8],"approach":[9,46],"to":[10,78],"Information":[11],"Extraction":[12],"by":[13,36],"combining":[14],"conventional":[15],"text":[16,25],"classification":[17],"techniques":[18],"and":[19,53],"Hidden":[20],"Markov":[21],"Models":[22],"(HMM).":[23],"A":[24],"classifier":[26],"generates":[27],"(locally":[29],"optimal)":[30],"initial":[31],"output,":[32],"which":[33],"is":[34],"refined":[35],"an":[37],"HMM,":[38],"providing":[39],"globally":[41],"optimal":[42],"classification.":[43],"The":[44],"proposed":[45],"was":[47,76],"evaluated":[48],"in":[49,60,90,115],"two":[50],"case":[51,71,100],"studies":[52],"the":[54,63,66,69,73,98,102],"experiments":[55],"revealed":[56],"consistent":[58],"gain":[59],"performance":[61],"through":[62],"use":[64],"of":[65,88,113],"HMM.":[67],"first":[70],"study,":[72,101],"implemented":[74],"prototype":[75,103],"used":[77],"extract":[79],"information":[80,105],"from":[81,106],"bibliographic":[82],"references,":[83],"reaching":[84,109],"precision":[86,111],"rate":[87,112],"87.48%":[89],"test":[92,117],"set":[93,118],"with":[94,119],"3000":[95],"references.":[96],"second":[99],"extracted":[104],"author":[107],"affiliations,":[108],"90.27%":[114],"300":[120],"affiliations.":[121]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}