{"id":"https://openalex.org/W3015651285","doi":"https://doi.org/10.1109/icassp40776.2020.9054695","title":"A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin","display_name":"A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015651285","doi":"https://doi.org/10.1109/icassp40776.2020.9054695","mag":"3015651285"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100353424","display_name":"Junhui Zhang","orcid":"https://orcid.org/0000-0003-4398-8568"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junhui Zhang","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026109787","display_name":"Junjie Pan","orcid":"https://orcid.org/0000-0002-7570-6927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Pan","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369916","display_name":"Chen Li","orcid":"https://orcid.org/0000-0003-1545-8885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682515","display_name":"Shichao Liu","orcid":"https://orcid.org/0000-0002-3163-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichao Liu","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354571","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6821-2710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance AI-Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI-Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100353424"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.121,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89620692,"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":"6694","last_page":"6698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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":0.9947999715805054,"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":0.8575190305709839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8226066827774048},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.747298002243042},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7279637455940247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6581010818481445},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5697986483573914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5582218766212463},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.43449363112449646},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.41616764664649963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36634397506713867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34497660398483276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09744781255722046}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8575190305709839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226066827774048},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.747298002243042},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7279637455940247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6581010818481445},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5697986483573914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5582218766212463},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.43449363112449646},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.41616764664649963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36634397506713867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34497660398483276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09744781255722046},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2158387599","https://openalex.org/W2160693947","https://openalex.org/W2161939545","https://openalex.org/W2164107060","https://openalex.org/W2251426526","https://openalex.org/W2546744831","https://openalex.org/W2610983683","https://openalex.org/W2747175885","https://openalex.org/W2807746654","https://openalex.org/W2896457183","https://openalex.org/W2924677654","https://openalex.org/W2945656493","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W4295276571","https://openalex.org/W4385245566","https://openalex.org/W6683362285","https://openalex.org/W6729005282","https://openalex.org/W6739901393","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W4362721699","https://openalex.org/W1653166271","https://openalex.org/W1495012990","https://openalex.org/W4282591925","https://openalex.org/W2963023579"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,19,23,38,68],"hybrid":[6],"text":[7,27,34,115],"normalization":[8,35,116],"system":[9,14,56,96],"using":[10],"multi-head":[11],"self-attention.":[12],"The":[13,51],"combines":[15],"the":[16,60,89,92,95],"advantages":[17],"of":[18,40,53,88,94],"rule-based":[20,114],"model":[21,25],"and":[22,66],"neural":[24,61],"for":[26],"preprocessing":[28],"tasks.":[29],"Previous":[30],"studies":[31,65],"in":[32],"Mandarin":[33],"usually":[36],"use":[37],"set":[39],"hand-written":[41],"rules,":[42],"which":[43],"are":[44],"hard":[45],"to":[46,82],"improve":[47],"on":[48,71,102],"general":[49],"cases.":[50],"idea":[52,105],"our":[54,72],"proposed":[55],"is":[57,97],"motivated":[58],"by":[59,99,110],"models":[62],"from":[63],"recent":[64],"has":[67],"better":[69],"performance":[70,93],"internal":[73],"news":[74],"corpus.":[75],"This":[76,104],"paper":[77],"also":[78],"includes":[79],"different":[80,111],"attempts":[81],"deal":[83],"with":[84,113],"imbalanced":[85],"pattern":[86],"distribution":[87],"dataset.":[90],"Overall,":[91],"improved":[98],"over":[100],"1.9%":[101],"sentence-level.":[103],"can":[106],"potentially":[107],"be":[108],"adopted":[109],"languages":[112],"systems.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}