{"id":"https://openalex.org/W2002343100","doi":"https://doi.org/10.1162/0891201054223986","title":"A General Technique to Train Language Models on Language Models","display_name":"A General Technique to Train Language Models on Language Models","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W2002343100","doi":"https://doi.org/10.1162/0891201054223986","mag":"2002343100"},"language":"en","primary_location":{"id":"doi:10.1162/0891201054223986","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201054223986","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201054223986","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201054223986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088112856","display_name":"Mark-Jan Nederhof","orcid":"https://orcid.org/0000-0002-1845-6829"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Mark-Jan Nederhof","raw_affiliation_strings":["University of Groningen","university of Groningen"],"affiliations":[{"raw_affiliation_string":"University of Groningen","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"university of Groningen","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088112856"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":3.0712,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91660517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":"2","first_page":"173","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9979000091552734,"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/T12031","display_name":"Speech and dialogue systems","score":0.9793999791145325,"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":0.8416895866394043},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.6645997762680054},{"id":"https://openalex.org/keywords/context-free-grammar","display_name":"Context-free grammar","score":0.6518099308013916},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6410182118415833},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6298873424530029},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6187268495559692},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.6133272647857666},{"id":"https://openalex.org/keywords/probabilistic-automaton","display_name":"Probabilistic automaton","score":0.6030192375183105},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5856749415397644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.527406632900238},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5207414627075195},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4891705811023712},{"id":"https://openalex.org/keywords/mildly-context-sensitive-grammar-formalism","display_name":"Mildly context-sensitive grammar formalism","score":0.44736433029174805},{"id":"https://openalex.org/keywords/grammar-induction","display_name":"Grammar induction","score":0.4217550754547119},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.2789823114871979},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.2681065797805786},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1834334433078766},{"id":"https://openalex.org/keywords/emergent-grammar","display_name":"Emergent grammar","score":0.1622387170791626},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.14713141322135925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08934691548347473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416895866394043},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6645997762680054},{"id":"https://openalex.org/C97212296","wikidata":"https://www.wikidata.org/wiki/Q338047","display_name":"Context-free grammar","level":3,"score":0.6518099308013916},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6410182118415833},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6298873424530029},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6187268495559692},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.6133272647857666},{"id":"https://openalex.org/C174784677","wikidata":"https://www.wikidata.org/wiki/Q176567","display_name":"Probabilistic automaton","level":3,"score":0.6030192375183105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5856749415397644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.527406632900238},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5207414627075195},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4891705811023712},{"id":"https://openalex.org/C172265290","wikidata":"https://www.wikidata.org/wiki/Q6134957","display_name":"Mildly context-sensitive grammar formalism","level":4,"score":0.44736433029174805},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.4217550754547119},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2789823114871979},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2681065797805786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1834334433078766},{"id":"https://openalex.org/C69298649","wikidata":"https://www.wikidata.org/wiki/Q6045214","display_name":"Emergent grammar","level":3,"score":0.1622387170791626},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.14713141322135925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08934691548347473},{"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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/0891201054223986","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201054223986","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201054223986","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:openaire/85b2b8a8-f12e-497c-95ba-1bd32edbcdb5","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/85b2b8a8-f12e-497c-95ba-1bd32edbcdb5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nederhof, MJ 2005, 'A general technique to train language models on language models', Computational Linguistics, vol. 31, no. 2, pp. 173-185. https://doi.org/10.1162/0891201054223986","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:c686ef0ecf2948f481e87df4dc88fee9","is_oa":true,"landing_page_url":"https://doaj.org/article/c686ef0ecf2948f481e87df4dc88fee9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 31, Iss 2 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/0891201054223986","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201054223986","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201054223986","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2002343100.pdf","grobid_xml":"https://content.openalex.org/works/W2002343100.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W89965911","https://openalex.org/W92394816","https://openalex.org/W124331494","https://openalex.org/W177913229","https://openalex.org/W1503669439","https://openalex.org/W1574901103","https://openalex.org/W1687940340","https://openalex.org/W1968330359","https://openalex.org/W2036540855","https://openalex.org/W2081516556","https://openalex.org/W2084162167","https://openalex.org/W2089385274","https://openalex.org/W2103005629","https://openalex.org/W2111041233","https://openalex.org/W2123099569","https://openalex.org/W2125529971","https://openalex.org/W2170336504","https://openalex.org/W2582290567","https://openalex.org/W4205167092"],"related_works":["https://openalex.org/W2951456305","https://openalex.org/W3107474891","https://openalex.org/W1587826772","https://openalex.org/W2464798123","https://openalex.org/W199912135","https://openalex.org/W2965013899","https://openalex.org/W2123538056","https://openalex.org/W1587931548","https://openalex.org/W2119143327","https://openalex.org/W2002343100"],"abstract_inverted_index":{"We":[0],"show":[1],"that":[2,39],"under":[3],"certain":[4],"conditions,":[5],"a":[6,16,27,34,53,69],"language":[7,18],"model":[8,64],"can":[9],"be":[10],"trained":[11,46],"on":[12,30,65],"the":[13,24,31,40,66],"basis":[14,32,67],"of":[15,23,33,56,68],"second":[17],"model.":[19],"The":[20],"main":[21],"instance":[22],"technique":[25],"trains":[26],"finite":[28],"automaton":[29,47],"probabilistic":[35,70],"context-free":[36,71],"grammar,":[37],"such":[38],"Kullback-Leibler":[41],"distance":[42],"between":[43],"grammar":[44],"and":[45],"is":[48,52],"provably":[49],"minimal.":[50],"This":[51],"substantial":[54],"generalization":[55],"an":[57,62],"existing":[58],"algorithm":[59],"to":[60],"train":[61],"n-gram":[63],"grammar.":[72]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}