{"id":"https://openalex.org/W2029061393","doi":"https://doi.org/10.3115/1118693.1118698","title":"Augmented mixture models for lexical disambiguation","display_name":"Augmented mixture models for lexical disambiguation","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W2029061393","doi":"https://doi.org/10.3115/1118693.1118698","mag":"2029061393"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118698","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118698","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118698","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040422637","display_name":"Silviu Cucerzan","orcid":"https://orcid.org/0009-0005-0773-0924"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Silviu Cucerzan","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD","Johns Hopkins University, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015876016","display_name":"David Yarowsky","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Yarowsky","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD","Johns Hopkins University, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.6844,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85172876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9980999827384949,"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":0.9944000244140625,"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":0.7528535723686218},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.7355074882507324},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6691418886184692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6399276852607727},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5399231314659119},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.5377810597419739},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5320996046066284},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5310203433036804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4977860450744629},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42734256386756897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40557175874710083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37161198258399963},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.17058756947517395},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.100929856300354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528535723686218},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.7355074882507324},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6691418886184692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399276852607727},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5399231314659119},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.5377810597419739},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5320996046066284},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5310203433036804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4977860450744629},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42734256386756897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40557175874710083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37161198258399963},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.17058756947517395},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.100929856300354}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1118693.1118698","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118698","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.5733","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.5733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/W/W02/W02-1005.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.3238","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.3238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/silviu/Papers/emnlp02.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118698","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118698","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118698","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2029061393.pdf","grobid_xml":"https://content.openalex.org/works/W2029061393.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W17280441","https://openalex.org/W196799388","https://openalex.org/W199321604","https://openalex.org/W1519443010","https://openalex.org/W1544407768","https://openalex.org/W1574901103","https://openalex.org/W1597379537","https://openalex.org/W1632767318","https://openalex.org/W1795234945","https://openalex.org/W1977182536","https://openalex.org/W1988790447","https://openalex.org/W2010595692","https://openalex.org/W2069781236","https://openalex.org/W2085606725","https://openalex.org/W2117400858","https://openalex.org/W2118996379","https://openalex.org/W2119966617","https://openalex.org/W2143635578","https://openalex.org/W2148426685","https://openalex.org/W2154834484","https://openalex.org/W2170699901","https://openalex.org/W2249186037","https://openalex.org/W2250369422","https://openalex.org/W2398845498","https://openalex.org/W2949916273","https://openalex.org/W2951797318","https://openalex.org/W2952192369","https://openalex.org/W2964062602","https://openalex.org/W3016210511","https://openalex.org/W3017143921","https://openalex.org/W4250516003"],"related_works":["https://openalex.org/W2327035729","https://openalex.org/W2348748958","https://openalex.org/W3039673966","https://openalex.org/W1538046993","https://openalex.org/W2884325279","https://openalex.org/W1570592793","https://openalex.org/W1525436954","https://openalex.org/W2385662756","https://openalex.org/W2585372724","https://openalex.org/W2241444561"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"several":[3,80],"augmented":[4],"mixture":[5,54],"models":[6,14,55,100],"that":[7,36,52,59],"are":[8,56,101],"competitive":[9],"alternatives":[10],"to":[11,17,21,91,104],"standard":[12,81],"Bayesian":[13],"and":[15,25,58,62,94],"prove":[16],"be":[18,105],"very":[19],"suitable":[20],"word":[22],"sense":[23],"disambiguation":[24],"related":[26],"classification":[27,33],"tasks.":[28],"We":[29,50],"present":[30],"a":[31],"new":[32],"correction":[34,65],"technique":[35,66],"successfully":[37],"addresses":[38],"the":[39,47,53,69,72,98],"problem":[40],"of":[41,43,71],"under-estimation":[42],"infrequent":[44],"classes":[45],"in":[46,84,108],"training":[48],"data.":[49],"show":[51],"boosting-friendly":[57],"both":[60],"Adaboost":[61],"our":[63],"original":[64],"can":[67],"improve":[68],"results":[70],"raw":[73],"model":[74],"significantly,":[75],"achieving":[76],"state-of-the-art":[77],"performance":[78],"on":[79],"test":[82],"sets":[83],"four":[85],"languages.":[86],"With":[87],"substantially":[88],"different":[89],"output":[90],"Na\u00efve":[92],"Bayes":[93],"other":[95],"statistical":[96],"methods,":[97],"investigated":[99],"also":[102],"shown":[103],"effective":[106],"participants":[107],"classifier":[109],"combination.":[110]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}