{"id":"https://openalex.org/W3197748976","doi":"https://doi.org/10.21437/interspeech.2021-1067","title":"On Sampling-Based Training Criteria for Neural Language Modeling","display_name":"On Sampling-Based Training Criteria for Neural Language Modeling","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197748976","doi":"https://doi.org/10.21437/interspeech.2021-1067","mag":"3197748976"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1067","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/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":["AppTek GmbH, 52062 Aachen, Germany","Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060583235","display_name":"David Thulke","orcid":"https://orcid.org/0000-0002-9808-7073"},"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":"David Thulke","raw_affiliation_strings":["AppTek GmbH, 52062 Aachen, Germany","Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","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":true,"raw_author_name":"Alexander Gerstenberger","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Khoa Viet Tran","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":"Khoa Viet Tran","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","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":["AppTek GmbH, 52062 Aachen, Germany","Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","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":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","AppTek GmbH, 52062 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, Computer Science Department RWTH Aachen University, 52074 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, 52062 Aachen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010929553"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56055404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1877","last_page":"1881"},"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":0.9991999864578247,"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":0.9987000226974487,"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":0.7536604404449463},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5841140747070312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4987983703613281},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.477058082818985},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4750392735004425},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.4678056538105011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4455238878726959},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43202969431877136},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42590391635894775},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4236869215965271},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4218427836894989},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.41677671670913696},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3633013367652893},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2960898280143738},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2899986803531647},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2887098789215088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.254550039768219},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16381648182868958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14915046095848083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536604404449463},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5841140747070312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4987983703613281},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.477058082818985},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4750392735004425},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.4678056538105011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4455238878726959},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43202969431877136},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42590391635894775},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4236869215965271},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4218427836894989},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.41677671670913696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3633013367652893},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2960898280143738},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2899986803531647},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2887098789215088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.254550039768219},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16381648182868958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14915046095848083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1067","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"},{"id":"https://openalex.org/F4320334679","display_name":"Research Executive Agency","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1558797106","https://openalex.org/W1614298861","https://openalex.org/W1768488313","https://openalex.org/W2026149468","https://openalex.org/W2120861206","https://openalex.org/W2152790380","https://openalex.org/W2259472270","https://openalex.org/W2406273144","https://openalex.org/W2463033603","https://openalex.org/W2496955520","https://openalex.org/W2516310076","https://openalex.org/W2799923439","https://openalex.org/W2807201985","https://openalex.org/W2896457183","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2949759968","https://openalex.org/W2953384591","https://openalex.org/W2962784628","https://openalex.org/W2963660642","https://openalex.org/W2964420626","https://openalex.org/W2972692349","https://openalex.org/W2980360762","https://openalex.org/W2981857663","https://openalex.org/W3034893234","https://openalex.org/W3162193499","https://openalex.org/W4288290348","https://openalex.org/W4292779060","https://openalex.org/W4294170691","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W1773599773","https://openalex.org/W2268150819","https://openalex.org/W2047632477"],"abstract_inverted_index":{"As":[0],"the":[1,27,31,41,47,55,92,106,110,134,167],"vocabulary":[2,33],"size":[3],"of":[4,21,50,57],"modern":[5],"word-based":[6],"language":[7,141],"models":[8],"becomes":[9],"ever":[10],"larger,":[11],"many":[12],"sampling-based":[13,156],"training":[14,111],"criteria":[15],"are":[16],"proposed":[17],"and":[18,61,86,102,143,149,161],"investigated.The":[19],"essence":[20],"these":[22,121],"sampling":[23,52,122],"methods":[24,53,123,157],"is":[25,54],"that":[26,119],"softmax-related":[28],"traversal":[29],"over":[30,67],"entire":[32],"can":[34,124],"be":[35],"simplified,":[36],"giving":[37,166],"speedups":[38],"compared":[39],"to":[40,91,109,113],"baseline.A":[42],"problem":[43],"we":[44,71,81,104,117,131],"notice":[45],"about":[46,64],"current":[48],"landscape":[49],"such":[51],"lack":[56],"a":[58,78],"systematic":[59],"comparison":[60],"some":[62,114],"myths":[63],"preferring":[65],"one":[66],"another.In":[68],"this":[69],"work,":[70],"consider":[72],"Monte":[73],"Carlo":[74],"sampling,":[75,77],"importance":[76],"novel":[79],"method":[80],"call":[82],"compensated":[83],"partial":[84],"summation,":[85],"noise":[87],"contrastive":[88],"estimation.Linking":[89],"back":[90],"three":[93],"traditional":[94],"criteria,":[95],"namely":[96],"mean":[97],"squared":[98],"error,":[99],"binary":[100],"cross-entropy,":[101],"crossentropy,":[103],"derive":[105],"theoretical":[107],"solutions":[108],"problems.Contrary":[112],"common":[115],"belief,":[116],"show":[118],"all":[120,155],"perform":[125],"equally":[126],"well,":[127],"as":[128,130],"long":[129],"correct":[132],"for":[133],"intended":[135],"class":[136],"posterior":[137],"probabilities.Experimental":[138],"results":[139],"in":[140],"modeling":[142],"automatic":[144],"speech":[145],"recognition":[146],"on":[147],"Switchboard":[148],"LibriSpeech":[150],"support":[151],"our":[152],"claim,":[153],"with":[154],"showing":[158],"similar":[159],"perplexities":[160],"word":[162],"error":[163],"rates":[164],"while":[165],"expected":[168],"speedups.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}