{"id":"https://openalex.org/W2129914454","doi":"https://doi.org/10.1109/slt.2010.5700892","title":"Lightly supervised learning of text normalization: Russian number names","display_name":"Lightly supervised learning of text normalization: Russian number names","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2129914454","doi":"https://doi.org/10.1109/slt.2010.5700892","mag":"2129914454"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2010.5700892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","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/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard Sproat","raw_affiliation_strings":["Google, Inc., USA","Google Inc., United States"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5063612469"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.3935,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.85533477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9886000156402588,"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":0.8088499307632446},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7527998089790344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6852890253067017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6414037346839905},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5685547590255737},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5350979566574097},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4384768605232239},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3238539695739746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1956622302532196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088499307632446},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7527998089790344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6852890253067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6414037346839905},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5685547590255737},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5350979566574097},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4384768605232239},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3238539695739746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1956622302532196},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2010.5700892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.73","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.73","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslu.ogi.edu/%7Esproatr/Courses/TextNorm/Papers/slt2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W74961537","https://openalex.org/W105344507","https://openalex.org/W135608829","https://openalex.org/W1499275966","https://openalex.org/W1605287260","https://openalex.org/W1967362851","https://openalex.org/W2008652694","https://openalex.org/W2079149759","https://openalex.org/W2108239140","https://openalex.org/W2164107060","https://openalex.org/W2462310159","https://openalex.org/W2499711517","https://openalex.org/W2787894218","https://openalex.org/W6605521863"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W4321441197","https://openalex.org/W4294432981","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Most":[0],"areas":[1],"of":[2,10,46,61,70,97,114,187],"natural":[3],"language":[4,105,156],"processing":[5],"today":[6],"make":[7],"heavy":[8],"use":[9],"automatic":[11],"inference":[12,96],"from":[13,57,122,180],"large":[14],"corpora.":[15],"One":[16,52],"exception":[17],"is":[18,28,78,168],"text-normalization":[19],"for":[20,37,54,174],"such":[21,38],"applications":[22],"as":[23,40],"text-to-speech":[24],"synthesis,":[25],"where":[26],"it":[27,167],"still":[29],"the":[30,44,58,68,95,123,160],"norm":[31],"to":[32,86,107,127,143,170],"build":[33],"grammars":[34],"by":[35],"hand":[36],"tasks":[39],"handling":[41],"abbreviations":[42],"or":[43],"expansion":[45,99,172],"digit":[47,128],"sequences":[48],"into":[49,147],"number":[50,118,148,177],"names.":[51],"reason":[53],"this,":[55],"apart":[56],"general":[59],"lack":[60,69],"interest":[62],"in":[63,100],"text":[64],"normalization,":[65],"has":[66],"been":[67],"annotated":[71],"data.":[72,162,190],"For":[73],"many":[74],"languages,":[75],"however,":[76],"there":[77],"abundant":[79],"unannotated":[80,181],"data":[81],"that":[82,166],"can":[83,140],"be":[84,141],"brought":[85],"bear":[87],"on":[88,94,159],"these":[89],"problems.":[90],"This":[91],"paper":[92],"reports":[93],"number-name":[98,133,138],"Russian,":[101],"a":[102,155,185],"particularly":[103],"difficult":[104],"due":[106],"its":[108],"complex":[109,176],"inflectional":[110],"system.":[111],"A":[112],"database":[113],"several":[115],"million":[116],"spelled-out":[117],"names":[119],"was":[120],"collected":[121],"web":[124,161],"and":[125,183],"mapped":[126],"strings":[129],"using":[130,154,184],"an":[131],"overgenerating":[132,137],"grammar.":[134],"The":[135],"same":[136],"grammar":[139],"used":[142],"produce":[144],"candidate":[145],"expansions":[146],"names,":[149],"which":[150],"are":[151],"then":[152],"scored":[153],"model":[157],"trained":[158],"Our":[163],"results":[164],"suggest":[165],"possible":[169],"infer":[171],"modules":[173],"very":[175],"name":[178],"systems,":[179],"data,":[182],"minimum":[186],"hand-compiled":[188],"seed":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}