{"id":"https://openalex.org/W57814663","doi":"https://doi.org/10.1007/3-540-36618-0_24","title":"Combining Naive Bayes and n-Gram Language Models for Text Classification","display_name":"Combining Naive Bayes and n-Gram Language Models for Text Classification","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W57814663","doi":"https://doi.org/10.1007/3-540-36618-0_24","mag":"57814663"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-36618-0_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36618-0_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5047400593","display_name":"Fuchun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Fuchun Peng","raw_affiliation_strings":["School of Computer Science, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, Canada, N2L 3G1"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, Canada, N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dale Schuurmans","raw_affiliation_strings":["School of Computer Science, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, Canada, N2L 3G1"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, Canada, N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047400593"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":5.7961,"has_fulltext":false,"cited_by_count":170,"citation_normalized_percentile":{"value":0.96628228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"335","last_page":"350"},"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":0.9991999864578247,"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/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.8283060789108276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455098628997803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6926383376121521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6646648645401001},{"id":"https://openalex.org/keywords/bayes-error-rate","display_name":"Bayes error rate","score":0.6565432548522949},{"id":"https://openalex.org/keywords/bayesian-programming","display_name":"Bayesian programming","score":0.6124699115753174},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.6038506031036377},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5917133092880249},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.42971867322921753},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.4263896942138672},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4184601902961731},{"id":"https://openalex.org/keywords/bayes-classifier","display_name":"Bayes classifier","score":0.39714425802230835},{"id":"https://openalex.org/keywords/bayes-factor","display_name":"Bayes factor","score":0.33829039335250854},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32839691638946533},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2865506410598755},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1424752175807953}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.8283060789108276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455098628997803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6926383376121521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6646648645401001},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.6565432548522949},{"id":"https://openalex.org/C127043819","wikidata":"https://www.wikidata.org/wiki/Q16243608","display_name":"Bayesian programming","level":5,"score":0.6124699115753174},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.6038506031036377},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5917133092880249},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.42971867322921753},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.4263896942138672},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4184601902961731},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.39714425802230835},{"id":"https://openalex.org/C142291917","wikidata":"https://www.wikidata.org/wiki/Q4165283","display_name":"Bayes factor","level":4,"score":0.33829039335250854},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32839691638946533},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2865506410598755},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1424752175807953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/3-540-36618-0_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36618-0_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.1184","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.1184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.people.umass.edu/fuchun/publication/ECIR03.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.8466","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.8466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.uwaterloo.ca/~dale/papers/ecir03.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W67881473","https://openalex.org/W91469012","https://openalex.org/W126937802","https://openalex.org/W179179905","https://openalex.org/W1490796714","https://openalex.org/W1507029541","https://openalex.org/W1522930027","https://openalex.org/W1533946607","https://openalex.org/W1550206324","https://openalex.org/W1574901103","https://openalex.org/W1817561967","https://openalex.org/W1924689489","https://openalex.org/W2043909051","https://openalex.org/W2045909430","https://openalex.org/W2075201173","https://openalex.org/W2082314883","https://openalex.org/W2093390569","https://openalex.org/W2097927681","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2131133093","https://openalex.org/W2140785063","https://openalex.org/W2147654806","https://openalex.org/W2158195707","https://openalex.org/W2158866759","https://openalex.org/W2165431734","https://openalex.org/W2611071497","https://openalex.org/W2800394774","https://openalex.org/W3017143921","https://openalex.org/W3110485210","https://openalex.org/W4206765718","https://openalex.org/W6602738186","https://openalex.org/W6632118081","https://openalex.org/W6737294430","https://openalex.org/W6776565550"],"related_works":["https://openalex.org/W2393473353","https://openalex.org/W2394466068","https://openalex.org/W1584413767","https://openalex.org/W179179905","https://openalex.org/W2041448365","https://openalex.org/W83434975","https://openalex.org/W51914556","https://openalex.org/W349770100","https://openalex.org/W1998749474","https://openalex.org/W1840577052"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}