{"id":"https://openalex.org/W2156279727","doi":"https://doi.org/10.1145/1194936.1194939","title":"An empirical study on language model adaptation","display_name":"An empirical study on language model adaptation","publication_year":2006,"publication_date":"2006-09-01","ids":{"openalex":"https://openalex.org/W2156279727","doi":"https://doi.org/10.1145/1194936.1194939","mag":"2156279727"},"language":"en","primary_location":{"id":"doi:10.1145/1194936.1194939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1194936.1194939","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-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/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Suzuki Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Suzuki Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100887075","display_name":"Hisami Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hisami Suzuki","raw_affiliation_strings":["Suzuki Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Suzuki Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081650208","display_name":"Wei Yuan","orcid":"https://orcid.org/0000-0003-4880-844X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yuan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3988,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85659179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"5","issue":"3","first_page":"209","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/discriminative-model","display_name":"Discriminative model","score":0.9027881622314453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7607815265655518},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6671364307403564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6392334699630737},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5388934016227722},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5319238901138306},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5294691324234009},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.46591001749038696},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.45383715629577637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42805033922195435},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4230252504348755},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.413251668214798},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3875918686389923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3492940664291382},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2415100336074829},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16594403982162476},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.15825888514518738},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1352270245552063},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.09088549017906189}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9027881622314453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607815265655518},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6671364307403564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392334699630737},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5388934016227722},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5319238901138306},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5294691324234009},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.46591001749038696},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.45383715629577637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42805033922195435},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4230252504348755},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.413251668214798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3875918686389923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3492940664291382},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2415100336074829},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16594403982162476},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.15825888514518738},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1352270245552063},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.09088549017906189},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1194936.1194939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1194936.1194939","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.3130","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.3130","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/~jfgao/paper/gao_suzuki_yuan.2006.talip.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W198953946","https://openalex.org/W1480376833","https://openalex.org/W1552767446","https://openalex.org/W1574901103","https://openalex.org/W1593239840","https://openalex.org/W1932968309","https://openalex.org/W1974967573","https://openalex.org/W2005614013","https://openalex.org/W2008652694","https://openalex.org/W2066099613","https://openalex.org/W2093478938","https://openalex.org/W2093525792","https://openalex.org/W2120084270","https://openalex.org/W2121127625","https://openalex.org/W2124445791","https://openalex.org/W2129818202","https://openalex.org/W2138309071","https://openalex.org/W2146574666","https://openalex.org/W2489487449","https://openalex.org/W2603415636","https://openalex.org/W2799061466","https://openalex.org/W2981264952","https://openalex.org/W3021452258","https://openalex.org/W3097169496","https://openalex.org/W3163547718","https://openalex.org/W6600815437","https://openalex.org/W6677810812","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W4318827931","https://openalex.org/W391620190","https://openalex.org/W2395910192","https://openalex.org/W2118877323","https://openalex.org/W2113687551","https://openalex.org/W2112752961","https://openalex.org/W2143264198","https://openalex.org/W3008648540","https://openalex.org/W2740361506","https://openalex.org/W4312246223"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"an":[3],"empirical":[4],"study":[5],"of":[6,28,36,61,73,83,98],"four":[7,48],"techniques":[8],"for":[9],"adapting":[10,43],"language":[11],"models,":[12,24],"including":[13],"a":[14,16,90,114],"maximum":[15],"posteriori":[17],"(MAP)":[18],"method":[19,116],"and":[20,102,129,138],"three":[21],"discriminative":[22,107],"training":[23],"in":[25,59,117,124],"the":[26,34,44,57,62,71,74,80,95,99,106,134],"application":[27],"Japanese":[29],"Kana-Kanji":[30],"conversion.":[31],"We":[32,86],"compare":[33],"performance":[35,97],"these":[37],"methods":[38,108],"from":[39],"various":[40],"angles":[41],"by":[42,67,78],"baseline":[45],"model":[46],"to":[47,55,113],"adaptation":[49,75,100,139],"domains.":[50,140],"In":[51],"particular,":[52],"we":[53],"attempt":[54],"interpret":[56],"results":[58],"terms":[60],"character":[63],"error":[64],"rate":[65],"(CER)":[66],"correlating":[68],"them":[69],"with":[70,94],"characteristics":[72],"domain,":[76],"measured":[77],"using":[79],"information-theoretic":[81],"notion":[82],"cross":[84],"entropy.":[85],"show":[87,104],"that":[88,105],"such":[89],"metric":[91],"correlates":[92],"well":[93],"CER":[96,120],"methods,":[101],"also":[103,123],"are":[109],"not":[110],"only":[111],"superior":[112],"MAP-based":[115],"achieving":[118],"larger":[119],"reduction,":[121],"but":[122],"having":[125],"fewer":[126],"side":[127],"effects":[128],"being":[130],"more":[131],"robust":[132],"against":[133],"similarity":[135],"between":[136],"background":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}