{"id":"https://openalex.org/W2079164875","doi":"https://doi.org/10.1145/1102351.1102471","title":"Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields","display_name":"Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2079164875","doi":"https://doi.org/10.1145/1102351.1102471","mag":"2079164875"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-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/A5100702016","display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0003-0467-8911"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Massachusetts Institute of Technology","University of Alberta"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000578217","display_name":"Shaomin Wang","orcid":"https://orcid.org/0000-0002-7244-7042"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Shaomin Wang","raw_affiliation_strings":["Massachusetts Institute of Technology","University of Alberta"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027200864","display_name":"Russell Greiner","orcid":"https://orcid.org/0000-0001-8327-934X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Russell Greiner","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dale Schuurmans","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100753413","display_name":"Li Cheng","orcid":"https://orcid.org/0000-0003-3261-3533"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Li Cheng","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100702016"],"corresponding_institution_ids":["https://openalex.org/I154425047","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.2854,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89516824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"948","last_page":"955"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/language-model","display_name":"Language model","score":0.7501431107521057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.704095721244812},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6918507814407349},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.6806039810180664},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.6728262901306152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5336495041847229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4840530753135681},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4516422748565674},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4444183111190796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38744404911994934}],"concepts":[{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7501431107521057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704095721244812},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6918507814407349},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6806039810180664},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.6728262901306152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336495041847229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4840530753135681},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4516422748565674},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4444183111190796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38744404911994934},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1102351.1102471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"},{"id":"pmh:oai:corescholar.libraries.wright.edu:knoesis-1105","is_oa":false,"landing_page_url":"https://corescholar.libraries.wright.edu/knoesis/106","pdf_url":null,"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:10.1.1.151.205","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~swang/icml2005.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.9237","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.9237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.machinelearning.org/proceedings/icml2005/papers/120_ExploitingSyntactic_WangEtAl.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.2982","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.2982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~greiner/PAPERS/SW-language-ICML2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W139420604","https://openalex.org/W1491175367","https://openalex.org/W1508165687","https://openalex.org/W1880262756","https://openalex.org/W1970961429","https://openalex.org/W1989705153","https://openalex.org/W1995875735","https://openalex.org/W1996903695","https://openalex.org/W2047706513","https://openalex.org/W2096175520","https://openalex.org/W2098126593","https://openalex.org/W2098678088","https://openalex.org/W2112971401","https://openalex.org/W2114858359","https://openalex.org/W2118714763","https://openalex.org/W2123893795","https://openalex.org/W2134237567","https://openalex.org/W2134731454","https://openalex.org/W2158195707","https://openalex.org/W2159863202","https://openalex.org/W2164469736","https://openalex.org/W3129711340"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2041167939","https://openalex.org/W2551914602","https://openalex.org/W1620568205","https://openalex.org/W2950575438","https://openalex.org/W2053242504","https://openalex.org/W79835312","https://openalex.org/W2123893795","https://openalex.org/W2223833155"],"abstract_inverted_index":{"We":[0,88,107],"present":[1],"a":[2,47,121],"directed":[3,35],"Markov":[4],"random":[5],"field":[6],"(MRF)":[7],"model":[8,37,152],"that":[9,139],"combines":[10],"n-gram":[11,83,98],"models,":[12],"probabilistic":[13,19],"context":[14,48],"free":[15],"grammars":[16],"(PCFGs)":[17],"and":[18,45,84,155],"latent":[20],"semantic":[21],"analysis":[22],"(PLSA)":[23],"for":[24],"the":[25,33,68,74,79,82,95,115,125,133,148],"purpose":[26],"of":[27,43,81,97,117,120],"statistical":[28],"language":[29,86,127],"modeling.":[30],"Even":[31],"though":[32],"composite":[34,126],"MRF":[36],"potentially":[38],"has":[39],"an":[40,63,110],"exponential":[41],"number":[42],"loops":[44],"becomes":[46],"sensitive":[49],"grammar,":[50],"we":[51,140],"are":[52,104],"nevertheless":[53],"able":[54],"to":[55,77,93,113,147],"estimate":[56],"its":[57],"parameters":[58],"in":[59,100,144],"cubic":[60],"time":[61],"using":[62],"efficient":[64],"modified":[65],"EM":[66],"method,":[67],"generalized":[69],"inside-outside":[70,75],"algorithm,":[71],"which":[72],"extends":[73],"algorithm":[76,112],"incorporate":[78],"effects":[80],"PLSA":[85],"models.":[87],"generalize":[89],"various":[90],"smoothing":[91],"techniques":[92],"alleviate":[94],"sparseness":[96],"counts":[99],"cases":[101],"where":[102],"there":[103],"hidden":[105],"variables.":[106],"also":[108],"derive":[109],"analogous":[111],"calculate":[114],"probability":[116],"initial":[118],"subsequence":[119],"sentence,":[122],"generated":[123],"by":[124],"model.":[128],"Our":[129],"experimental":[130],"results":[131],"on":[132],"Wall":[134],"Street":[135],"Journal":[136],"corpus":[137],"show":[138],"obtain":[141],"significant":[142],"reductions":[143],"perplexity":[145],"compared":[146],"state-of-the-art":[149],"baseline":[150],"trigram":[151],"with":[153],"Good-Turing":[154],"Kneser-Ney":[156],"smoothings.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}