{"id":"https://openalex.org/W4297841344","doi":"https://doi.org/10.21437/interspeech.2022-10864","title":"Thutmose Tagger: Single-pass neural model for Inverse Text Normalization","display_name":"Thutmose Tagger: Single-pass neural model for Inverse Text Normalization","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841344","doi":"https://doi.org/10.21437/interspeech.2022-10864"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10864","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/A5080844333","display_name":"Alexandra Antonova","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexandra Antonova","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066445347","display_name":"Evelina Bakhturina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evelina Bakhturina","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080844333"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41505064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"550","last_page":"554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9879000186920166,"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/normalization","display_name":"Normalization (sociology)","score":0.7828421592712402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435522675514221},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5964863896369934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5866389274597168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4375225901603699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4280606210231781},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1612955629825592}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7828421592712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435522675514221},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5964863896369934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866389274597168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4375225901603699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4280606210231781},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1612955629825592},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10864","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2156985047","https://openalex.org/W2749051922","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2924677654","https://openalex.org/W2970744242","https://openalex.org/W2972880214","https://openalex.org/W3016252185","https://openalex.org/W3154516348","https://openalex.org/W3160789530","https://openalex.org/W3169483174","https://openalex.org/W3194932072","https://openalex.org/W4288089799","https://openalex.org/W4295276571"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Inverse":[0],"text":[1],"normalization":[2],"(ITN)":[3],"is":[4,112,119,160,180],"an":[5],"essential":[6],"post-processing":[7,157],"step":[8],"in":[9,169],"automatic":[10],"speech":[11],"recognition":[12],"(ASR).It":[13],"converts":[14],"numbers,":[15],"dates,":[16],"abbreviations,":[17],"and":[18,41,127,135,142,154,165,173],"other":[19],"semiotic":[20],"classes":[21],"from":[22],"the":[23,122,146,149,174,178],"spoken":[24],"form":[25],"generated":[26],"by":[27],"ASR":[28],"to":[29,46,54,59,84,115,167,176],"their":[30],"written":[31],"forms.One":[32],"can":[33],"consider":[34],"ITN":[35,74,108],"as":[36,75,182],"a":[37,67,76,81,98],"Machine":[38],"Translation":[39],"task":[40],"use":[42],"neural":[43,50],"sequence-tosequence":[44],"models":[45,51,164],"solve":[47],"it.Unfortunately,":[48],"such":[49],"are":[52],"prone":[53,114],"hallucinations":[55],"that":[56,72],"could":[57],"lead":[58],"unacceptable":[60],"errors.To":[61],"mitigate":[62],"this":[63],"issue,":[64],"we":[65],"propose":[66],"single-pass":[68],"token":[69,87],"classifier":[70],"model":[71,79,111,118,159,172],"regards":[73],"tagging":[77],"task.The":[78],"assigns":[80],"replacement":[82],"fragment":[83],"every":[85],"input":[86,143],"or":[88,93],"marks":[89],"it":[90],"for":[91,156],"deletion":[92],"copying":[94],"without":[95],"changes.We":[96],"present":[97],"method":[99],"of":[100,107,148,184],"dataset":[101,126,179],"preparation,":[102],"based":[103],"on":[104,121,132],"granular":[105],"alignment":[106],"examples.The":[109],"proposed":[110],"less":[113],"hallucination":[116],"errors.The":[117],"trained":[120],"Google":[123],"Text":[124],"Normalization":[125],"achieves":[128],"state-of-the-art":[129],"sentence":[130],"accuracy":[131],"both":[133],"English":[134],"Russian":[136],"test":[137],"sets.One-to-one":[138],"correspondence":[139],"between":[140],"tags":[141],"words":[144],"improves":[145],"interpretability":[147],"model's":[150],"predictions,":[151],"simplifies":[152],"debugging,":[153],"allows":[155],"corrections.The":[158],"simpler":[161],"than":[162],"sequence-to-sequence":[163],"easier":[166],"optimize":[168],"production":[170],"settings.The":[171],"code":[175],"prepare":[177],"published":[181],"part":[183],"NeMo":[185],"project":[186],"1":[187],".":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}