{"id":"https://openalex.org/W2098737404","doi":"https://doi.org/10.1109/iwfhr.2004.98","title":"Stability Measure of Entropy Estimate and Its Application to Language Model Evaluation","display_name":"Stability Measure of Entropy Estimate and Its Application to Language Model Evaluation","publication_year":2004,"publication_date":"2004-12-23","ids":{"openalex":"https://openalex.org/W2098737404","doi":"https://doi.org/10.1109/iwfhr.2004.98","mag":"2098737404"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwfhr.2004.98","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5100295829","display_name":"Jahwan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"None Jahwan Kim","raw_affiliation_strings":["Div. of CS, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Div. of CS, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111432971","display_name":"Sungho Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134443","display_name":"Daejeon Institute of Science and Technology","ror":"https://ror.org/032qr1v70","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210134443"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"None Sungho Ryu","raw_affiliation_strings":["Div. of CS, KAIST, Daejeon, South Korea","Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR","institution_ids":["https://openalex.org/I4210134443","https://openalex.org/I157485424"]},{"raw_affiliation_string":"Div. of CS, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426073","display_name":"Jung Ho Kim","orcid":"https://orcid.org/0000-0003-4931-3553"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"J.H. Kim","raw_affiliation_strings":["Div. of CS, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Div. of CS, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":61},"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"461"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983,"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":0.9983,"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":0.9976,"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":0.9904,"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":[],"concepts":[{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.6211729},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5961937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5425135},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5385185},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4892454},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4779732},{"id":"https://openalex.org/C60507348","wikidata":"https://www.wikidata.org/wiki/Q6795892","display_name":"Maximum entropy probability distribution","level":3,"score":0.44884735},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.43402153},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4328583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.42468646},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.37545264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36565906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14813334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.123005},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1096876},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07874456},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwfhr.2004.98","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W1988520084","https://openalex.org/W1992536060","https://openalex.org/W2076118331","https://openalex.org/W2082092506","https://openalex.org/W2095817904","https://openalex.org/W2097927681","https://openalex.org/W2099111195","https://openalex.org/W2120062331","https://openalex.org/W2134237567","https://openalex.org/W2611071497","https://openalex.org/W2912934387","https://openalex.org/W2950186769","https://openalex.org/W4212883601","https://openalex.org/W4233559841","https://openalex.org/W4389015749"],"related_works":["https://openalex.org/W59993211","https://openalex.org/W4385752617","https://openalex.org/W3041490575","https://openalex.org/W3021846434","https://openalex.org/W2970690932","https://openalex.org/W2889261288","https://openalex.org/W2351977092","https://openalex.org/W2068679119","https://openalex.org/W2064875109","https://openalex.org/W2034921015"],"abstract_inverted_index":{"We":[0,67],"propose":[1,93],"in":[2,43,75,119],"this":[3,94],"paper":[4],"a":[5,29,125],"stability":[6,97,161],"measure":[7,98,157],"of":[8,15,54,72,82,99,162],"entropy":[9,100,164],"estimate":[10,60,85],"based":[11],"on":[12,149],"the":[13,21,34,58,62,64,70,80,83,134,139,145,155,160],"principle":[14],"Bayesian":[16,65],"statistics.":[17],"Stability,":[18],"or":[19],"how":[20],"estimates":[22,53,111],"vary":[23],"as":[24,42,96],"training":[25],"set":[26],"does,":[27],"is":[28,39,74,88,117,142],"critical":[30],"issue":[31],"especially":[32],"for":[33,107],"problems":[35],"where":[36,110],"parameter-to-data":[37],"ratio":[38],"extremely":[40],"high":[41],"language":[44,108],"modeling":[45],"and":[46,61,92,137],"text":[47],"compression.":[48],"There":[49],"are":[50,112],"two":[51,150],"natural":[52],"entropy,":[55],"one":[56],"being":[57],"classical":[59,84,163],"other":[63],"estimate.":[66,101],"show":[68,153],"that":[69,129,138,154],"difference":[71,95],"them":[73],"strong":[76],"positive":[77],"correlation":[78],"with":[79,133],"variance":[81],"when":[86],"it":[87,106],"not":[89,118],"so":[90,128],"small,":[91],"In":[102],"order":[103],"to":[104,123],"evaluate":[105],"models":[109],"available":[113],"but":[114],"posterior":[115],"distribution":[116,127],"general,":[120],"we":[121],"suggest":[122],"use":[124],"Dirichlet":[126],"its":[130],"expectation":[131],"agrees":[132],"estimated":[135],"parameters":[136],"total":[140],"count":[141],"preserved":[143],"at":[144],"same":[146],"time.":[147],"Experiments":[148],"benchmark":[151],"corpora":[152],"proposed":[156],"indeed":[158],"reflects":[159],"estimates.":[165]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2098737404","counts_by_year":[],"updated_date":"2024-12-09T03:49:26.917829","created_date":"2016-06-24"}