{"id":"https://openalex.org/W3094987082","doi":"https://doi.org/10.21437/interspeech.2020-2909","title":"Efficient MDI Adaptation for n-Gram Language Models","display_name":"Efficient MDI Adaptation for n-Gram Language Models","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094987082","doi":"https://doi.org/10.21437/interspeech.2020-2909","mag":"3094987082"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2909","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5007094260","display_name":"Ruizhe Huang","orcid":"https://orcid.org/0009-0005-6031-3775"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruizhe Huang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343462","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-9206-0892"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102995840","display_name":"Ashish Arora","orcid":"https://orcid.org/0000-0002-0530-2388"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Arora","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007094260"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63970872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4916","last_page":"4920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9997000098228455,"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":0.9993000030517578,"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/adaptation","display_name":"Adaptation (eye)","score":0.6499334573745728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.637787938117981},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5816834568977356},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.4726268947124481},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41991251707077026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35700076818466187},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12650522589683533},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06878489255905151}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6499334573745728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637787938117981},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5816834568977356},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.4726268947124481},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41991251707077026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35700076818466187},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12650522589683533},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06878489255905151},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2909","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W7542544","https://openalex.org/W17500809","https://openalex.org/W36200081","https://openalex.org/W63883758","https://openalex.org/W82457882","https://openalex.org/W140816929","https://openalex.org/W169286004","https://openalex.org/W179707045","https://openalex.org/W182840523","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1590952807","https://openalex.org/W1597533204","https://openalex.org/W1631260214","https://openalex.org/W1823613926","https://openalex.org/W1996903695","https://openalex.org/W2001792610","https://openalex.org/W2020073413","https://openalex.org/W2046932483","https://openalex.org/W2049901611","https://openalex.org/W2050971845","https://openalex.org/W2117793990","https://openalex.org/W2127049133","https://openalex.org/W2408082508","https://openalex.org/W2511530731","https://openalex.org/W2514741789","https://openalex.org/W2611669587","https://openalex.org/W2888867175","https://openalex.org/W2946595319","https://openalex.org/W2972399846"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W2250909759","https://openalex.org/W1901380241","https://openalex.org/W2532616038","https://openalex.org/W2787311093"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,19],"efficient":[4],"algorithm":[5,117],"for":[6,37,64,106],"n-gram":[7,53],"language":[8,21,39,68],"model":[9,22,40,54],"adaptation":[10,41,75,104,124],"under":[11],"the":[12,27,33,49,56,83,90,113],"minimum":[13],"discrimination":[14],"information":[15],"(MDI)":[16],"principle,":[17],"where":[18],"out-of-domain":[20],"is":[23,42,97],"adapted":[24],"to":[25,82,136],"satisfy":[26],"constraints":[28],"of":[29,32,48,52,58,115],"marginal":[30],"probabilities":[31],"in-domain":[34],"data.The":[35],"challenge":[36],"MDI":[38,74,96,103,123],"its":[43],"computational":[44],"complexity.By":[45],"taking":[46],"advantage":[47],"backoff":[50],"structure":[51],"and":[55,109],"idea":[57],"hierarchical":[59],"training":[60],"method,":[61],"originally":[62],"proposed":[63],"maximum":[65],"entropy":[66],"(ME)":[67],"models":[69],"[1],":[70],"we":[71],"show":[72],"that":[73],"can":[76],"be":[77],"computed":[78],"in":[79,85],"linear-time":[80],"complexity":[81,88],"inputs":[84],"each":[86],"iteration.The":[87],"remains":[89],"same":[91],"as":[92],"ME":[93],"models,":[94],"although":[95],"more":[98],"general":[99],"than":[100],"ME.This":[101],"makes":[102],"practical":[105],"large":[107,120],"corpus":[108],"vocabulary.Experimental":[110],"results":[111,134],"confirm":[112],"scalability":[114],"our":[116],"on":[118],"very":[119],"datasets,":[121],"while":[122],"gets":[125],"slightly":[126],"worse":[127],"perplexity":[128],"but":[129],"better":[130],"word":[131],"error":[132],"rate":[133],"compared":[135],"simple":[137],"linear":[138],"interpolation.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}