{"id":"https://openalex.org/W1840442643","doi":"https://doi.org/10.1109/icassp.2003.1198796","title":"Semantic n-gram language modeling with the latent maximum entropy principle","display_name":"Semantic n-gram language modeling with the latent maximum entropy principle","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1840442643","doi":"https://doi.org/10.1109/icassp.2003.1198796","mag":"1840442643"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198796","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://corescholar.libraries.wright.edu/cgi/viewcontent.cgi?article=1280&context=knoesis","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100702012","display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0002-3680-9464"},"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":"Shaojun Wang","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","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":"D. Schuurmans","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","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":false,"raw_author_name":"Fuchun Peng","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Department of Computer Engineering and Computer Science, University of Missouri at Columbia, USA","Department of Computer Engineering and Computer Science, University of Missouri, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Computer Science, University of Missouri at Columbia, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Department of Computer Engineering and Computer Science, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5538,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90125602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9810000061988831,"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/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.8430118560791016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7977905869483948},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6486995816230774},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6340013146400452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012167930603027},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5973163843154907},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5301987528800964},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5151214003562927},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.506888210773468},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4881764054298401},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.48287370800971985},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4769957363605499},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.4434516727924347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20086133480072021},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.13804835081100464},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.10506066679954529}],"concepts":[{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.8430118560791016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977905869483948},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6486995816230774},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6340013146400452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012167930603027},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5973163843154907},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5301987528800964},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5151214003562927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.506888210773468},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4881764054298401},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.48287370800971985},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4769957363605499},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.4434516727924347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20086133480072021},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.13804835081100464},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.10506066679954529},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2003.1198796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198796","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:corescholar.libraries.wright.edu:knoesis-1280","is_oa":true,"landing_page_url":"https://corescholar.libraries.wright.edu/knoesis/279","pdf_url":"https://corescholar.libraries.wright.edu/cgi/viewcontent.cgi?article=1280&context=knoesis","source":{"id":"https://openalex.org/S2737205702","display_name":"Journal of Bioresource Management","issn_l":"2309-3854","issn":["2309-3854"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310316536","host_organization_name":"Bioresource Research Center (BRC), Islamabad","host_organization_lineage":["https://openalex.org/P4310316536"],"host_organization_lineage_names":["Bioresource Research Center (BRC), Islamabad"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kno.e.sis Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.7914","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.7914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai2.uwaterloo.ca/~f3peng/publication/icassp03.ps","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:corescholar.libraries.wright.edu:knoesis-1280","is_oa":true,"landing_page_url":"https://corescholar.libraries.wright.edu/knoesis/279","pdf_url":"https://corescholar.libraries.wright.edu/cgi/viewcontent.cgi?article=1280&context=knoesis","source":{"id":"https://openalex.org/S2737205702","display_name":"Journal of Bioresource Management","issn_l":"2309-3854","issn":["2309-3854"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310316536","host_organization_name":"Bioresource Research Center (BRC), Islamabad","host_organization_lineage":["https://openalex.org/P4310316536"],"host_organization_lineage_names":["Bioresource Research Center (BRC), Islamabad"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kno.e.sis Publications","raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1840442643.pdf","grobid_xml":"https://content.openalex.org/works/W1840442643.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1007293483","https://openalex.org/W1995875735","https://openalex.org/W1996903695","https://openalex.org/W2001792610","https://openalex.org/W2049633694","https://openalex.org/W2096175520","https://openalex.org/W2114858359","https://openalex.org/W2118714763","https://openalex.org/W2134731454","https://openalex.org/W2160842254","https://openalex.org/W2163306339","https://openalex.org/W2164469736","https://openalex.org/W3049188988","https://openalex.org/W3129711340","https://openalex.org/W6674650171","https://openalex.org/W6790626572","https://openalex.org/W7041975391"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W1945850644","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2949456575","https://openalex.org/W2008468404"],"abstract_inverted_index":{"We":[0,69,82],"describe":[1,70],"a":[2,64],"unified":[3],"probabilistic":[4],"framework":[5,52],"for":[6,40,73,87],"statistical":[7],"language":[8,41,67],"modeling-the":[9],"latent":[10],"maximum":[11,37],"entropy":[12,38],"principle-which":[13],"can":[14],"effectively":[15],"incorporate":[16],"various":[17],"aspects":[18],"of":[19],"natural":[20],"language,":[21],"such":[22],"as":[23],"local":[24],"word":[25],"interaction,":[26],"syntactic":[27],"structure":[28],"and":[29,76],"semantic":[30],"document":[31],"information.":[32],"Unlike":[33],"previous":[34],"work":[35],"on":[36,90],"methods":[39],"modeling,":[42],"which":[43],"only":[44],"allow":[45],"explicit":[46],"features":[47,58],"to":[48,59],"be":[49,60],"modeled,":[50],"our":[51,79,88],"also":[53],"allows":[54],"relationships":[55],"over":[56],"hidden":[57],"captured,":[61],"resulting":[62],"in":[63,78],"more":[65],"expressive":[66],"model.":[68],"efficient":[71],"algorithms":[72],"marginalization,":[74],"inference":[75],"normalization":[77],"extended":[80],"models.":[81],"then":[83],"present":[84],"experimental":[85],"results":[86],"approach":[89],"the":[91],"Wall":[92],"Street":[93],"Journal":[94],"corpus.":[95]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}