{"id":"https://openalex.org/W4319862699","doi":"https://doi.org/10.1109/slt54892.2023.10022565","title":"Efficient Text Analysis with Pre-Trained Neural Network Models","display_name":"Efficient Text Analysis with Pre-Trained Neural Network Models","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862699","doi":"https://doi.org/10.1109/slt54892.2023.10022565"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022565","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022565","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5100537267","display_name":"Jia Cui","orcid":"https://orcid.org/0000-0002-7118-0198"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Cui","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["Emory University"],"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074469791","display_name":"Liqiang He","orcid":"https://orcid.org/0000-0001-9179-6398"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang He","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062105912","display_name":"Guangzhi Li","orcid":"https://orcid.org/0009-0004-9197-7737"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Li","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Seattle","Tencent AI Lab, Seattle"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Seattle","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100537267"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.3391,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.45497137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"676"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.857388973236084},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6834368109703064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6709868907928467},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6272414922714233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5935800671577454},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.5896072387695312},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5302193760871887},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4936405420303345},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4888898432254791},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4139111042022705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3789866268634796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3221045732498169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.857388973236084},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6834368109703064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6709868907928467},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6272414922714233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5935800671577454},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.5896072387695312},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5302193760871887},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4936405420303345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4888898432254791},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4139111042022705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3789866268634796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3221045732498169},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022565","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022565","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W153332557","https://openalex.org/W1507805082","https://openalex.org/W1606556647","https://openalex.org/W1973424788","https://openalex.org/W2097478551","https://openalex.org/W2113851376","https://openalex.org/W2150622925","https://openalex.org/W2164280277","https://openalex.org/W2293206651","https://openalex.org/W2529639179","https://openalex.org/W2545909488","https://openalex.org/W2612007440","https://openalex.org/W2747175885","https://openalex.org/W2786179895","https://openalex.org/W2806253224","https://openalex.org/W2896457183","https://openalex.org/W2924677654","https://openalex.org/W2945656493","https://openalex.org/W2950176361","https://openalex.org/W2963299674","https://openalex.org/W2970557265","https://openalex.org/W2971033911","https://openalex.org/W2972585802","https://openalex.org/W2978017171","https://openalex.org/W3015680182","https://openalex.org/W3016224472","https://openalex.org/W3035317912","https://openalex.org/W3101954944","https://openalex.org/W3103884771","https://openalex.org/W3105966348","https://openalex.org/W3113850747","https://openalex.org/W3161760609","https://openalex.org/W3174461835","https://openalex.org/W3176023514","https://openalex.org/W4221166186","https://openalex.org/W4288351520","https://openalex.org/W4301349660","https://openalex.org/W6674467793","https://openalex.org/W6681987038","https://openalex.org/W6755207826","https://openalex.org/W6757635932","https://openalex.org/W6766152879","https://openalex.org/W6766433015","https://openalex.org/W6767718706","https://openalex.org/W6768851824","https://openalex.org/W6788095661","https://openalex.org/W6809893488"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W2372867461","https://openalex.org/W2360709244"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,25,41,48,108,116,130,138],"application":[4],"of":[5,80],"pre-trained":[6],"BERT":[7,27,75],"model":[8,85],"in":[9,38],"three":[10],"classic":[11],"text":[12,17,103],"analysis":[13],"tasks:":[14],"Chinese":[15],"grapheme-to-phoneme(G2P),":[16],"normalization(TN)":[18],"and":[19,47,123,127],"sentence":[20,109],"punctuation":[21],"annotation.":[22],"Even":[23],"though":[24],"full-sized":[26],"has":[28,132],"prominent":[29],"modeling":[30],"power,":[31],"there":[32],"are":[33],"two":[34],"challenges":[35],"for":[36,43,65],"it":[37],"real":[39],"applications:":[40],"requirement":[42],"annotated":[44],"training":[45,63],"data":[46],"considerable":[49],"computational":[50],"cost.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,67],"propose":[56,99],"BERT-based":[57],"low-latency":[58],"solutions.":[59],"To":[60],"collect":[61],"sufficient":[62],"corpus":[64],"G2P,":[66],"transfer":[68],"knowledge":[69],"from":[70,91,137],"existing":[71],"rule-based":[72,117],"system":[73],"to":[74,115],"through":[76],"a":[77,100],"large":[78],"amount":[79],"unlabeled":[81],"corpus.":[82],"The":[83],"new":[84],"could":[86],"convert":[87],"all":[88],"characters":[89],"directly":[90],"raw":[92],"texts":[93],"with":[94],"higher":[95],"accuracy.":[96],"We":[97,119],"also":[98],"hybrid":[101],"two-stage":[102],"normalization":[104],"pipeline":[105],"which":[106],"reduces":[107],"error":[110],"rate":[111],"by":[112],"25%":[113],"compared":[114],"system.":[118],"offer":[120],"both":[121],"supervised":[122,125],"weakly":[124],"versions":[126],"find":[128],"that":[129],"latter":[131],"only":[133],"1%":[134],"accuracy":[135],"drop":[136],"former.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}