{"id":"https://openalex.org/W3213809193","doi":"https://doi.org/10.21437/interspeech.2022-10588","title":"Self-Normalized Importance Sampling for Neural Language Modeling","display_name":"Self-Normalized Importance Sampling for Neural Language Modeling","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3213809193","doi":"https://doi.org/10.21437/interspeech.2022-10588","mag":"3213809193"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10588","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5055490509","display_name":"Zijian Gy\u0151z\u0151 Yang","orcid":"https://orcid.org/0000-0001-9955-860X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zijian Yang","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046577673","display_name":"Yingbo Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yingbo Gao","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010929553","display_name":"Alexander Gerstenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Gerstenberger","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103460664","display_name":"Jintao Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jintao Jiang","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055490509"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2221504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3909","last_page":"3913"},"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/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.8379580974578857},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7972466945648193},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6683526039123535},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6248471736907959},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6118762493133545},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5439772605895996},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5110324621200562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49586495757102966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4708302319049835},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45772063732147217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4182116389274597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3691418468952179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3288657069206238},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07738125324249268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379580974578857},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7972466945648193},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6683526039123535},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6248471736907959},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6118762493133545},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5439772605895996},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5110324621200562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49586495757102966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4708302319049835},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45772063732147217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4182116389274597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3691418468952179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3288657069206238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07738125324249268},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10588","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1520465330","https://openalex.org/W1558797106","https://openalex.org/W1985258458","https://openalex.org/W2026149468","https://openalex.org/W2120861206","https://openalex.org/W2152790380","https://openalex.org/W2153579005","https://openalex.org/W2259472270","https://openalex.org/W2402268235","https://openalex.org/W2463033603","https://openalex.org/W2496955520","https://openalex.org/W2842511635","https://openalex.org/W2943845043","https://openalex.org/W2950577311","https://openalex.org/W2956159074","https://openalex.org/W2963403868","https://openalex.org/W2963660642","https://openalex.org/W2963882304","https://openalex.org/W3094852745","https://openalex.org/W3162193499","https://openalex.org/W3197748976"],"related_works":["https://openalex.org/W4285298148","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"To":[0],"mitigate":[1],"the":[2,9,13,29,43,77,102,110,127],"problem":[3],"of":[4,16,31,45,53,59,76],"having":[5],"to":[6,123,140],"traverse":[7],"over":[8],"full":[10],"vocabulary":[11,33],"in":[12,28,57,66,130,167],"softmax":[14],"normalization":[15],"a":[17,51,143],"neural":[18,35],"language":[19,36,148],"model,":[20],"sampling-based":[21,86],"training":[22,39,47,150],"criteria":[23,40,87,128],"are":[24,133],"proposed":[25,161],"and":[26,48,61,135,170],"investigated":[27],"context":[30],"large":[32],"word-based":[34],"models.":[37],"These":[38],"typically":[41],"enjoy":[42],"benefit":[44],"faster":[46],"testing,":[49],"at":[50],"cost":[52],"slightly":[54],"degraded":[55],"performance":[56],"terms":[58],"perplexity":[60],"almost":[62],"no":[63,138],"visible":[64],"drop":[65],"word":[67],"error":[68],"rate.":[69],"While":[70],"noise":[71],"contrastive":[72],"estimation":[73],"is":[74,99,107,137,165],"one":[75],"most":[78],"popular":[79],"choices,":[80],"recently":[81],"we":[82,117,157],"show":[83,158],"that":[84,159],"other":[85],"can":[88],"also":[89],"perform":[90],"well,":[91],"as":[92,94,151,153],"long":[93],"an":[95],"extra":[96],"correction":[97,144],"step":[98],"done,":[100],"where":[101],"intended":[103],"class":[104],"posterior":[105],"probability":[106],"recovered":[108],"from":[109],"raw":[111],"model":[112,149],"outputs.":[113],"In":[114],"this":[115,131],"work,":[116,126],"propose":[118],"self-normalized":[119,134,147,162],"importance":[120,163],"sampling.":[121],"Compared":[122],"our":[124,160],"previous":[125],"considered":[129],"work":[132],"there":[136],"need":[139],"further":[141],"conduct":[142],"step.":[145],"Through":[146],"well":[152],"lattice":[154],"rescoring":[155],"experiments,":[156],"sampling":[164],"competitive":[166],"both":[168],"research-oriented":[169],"production-oriented":[171],"automatic":[172],"speech":[173],"recognition":[174],"tasks.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}