{"id":"https://openalex.org/W4405633760","doi":"https://doi.org/10.1109/mlnlp63328.2024.10800442","title":"Improving Chinese Punctuation Restoration via External POS Tagger","display_name":"Improving Chinese Punctuation Restoration via External POS Tagger","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4405633760","doi":"https://doi.org/10.1109/mlnlp63328.2024.10800442"},"language":"en","primary_location":{"id":"doi:10.1109/mlnlp63328.2024.10800442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlnlp63328.2024.10800442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Machine Learning and Natural Language Processing (MLNLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018509871","display_name":"Dejun Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejun Gao","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunhai Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhai Miao","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinzi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I2799376586","display_name":"The Scarborough Hospital","ror":"https://ror.org/04pzgb662","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799376586"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xinzi Huang","raw_affiliation_strings":["University of Toronto Scarborough,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto Scarborough,Canada","institution_ids":["https://openalex.org/I2799376586","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113414416","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0002-8298-4378"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070212878","display_name":"Tingting Zhang","orcid":"https://orcid.org/0000-0002-7033-5418"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Zhang","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yinan Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinan Dai","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101766781","display_name":"Chunli Chen","orcid":"https://orcid.org/0000-0002-6464-4580"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunli Chen","raw_affiliation_strings":["China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Hangzhou) Information Technology Co., Ltd.,HangZhou,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9796000123023987,"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":0.9796000123023987,"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":0.9280999898910522,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9024999737739563,"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/punctuation","display_name":"Punctuation","score":0.8548163175582886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880073547363281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49528923630714417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40096282958984375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.353763222694397}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8548163175582886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880073547363281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49528923630714417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40096282958984375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.353763222694397}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlnlp63328.2024.10800442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlnlp63328.2024.10800442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Machine Learning and Natural Language Processing (MLNLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2085621450","https://openalex.org/W2513522215","https://openalex.org/W2781510043","https://openalex.org/W2899902398","https://openalex.org/W2937326859","https://openalex.org/W2938722449","https://openalex.org/W2946119234","https://openalex.org/W2963351448","https://openalex.org/W3016128928","https://openalex.org/W3094965760","https://openalex.org/W3096726003","https://openalex.org/W3106905592","https://openalex.org/W3166192435","https://openalex.org/W3185113268","https://openalex.org/W3196445330","https://openalex.org/W3200033622","https://openalex.org/W4221166827","https://openalex.org/W4385245566","https://openalex.org/W4402112368","https://openalex.org/W6731992975","https://openalex.org/W6765072895"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4],"typically":[5],"generate":[6],"transcriptions":[7],"without":[8],"punctuation.":[9],"To":[10],"enhance":[11,71],"readability":[12],"and":[13,93],"meet":[14],"the":[15,35,61,82,88,109,114,117,132],"expected":[16],"input":[17],"requirements":[18],"for":[19,121,150],"downstream":[20],"language":[21,128],"models,":[22],"it's":[23],"crucial":[24],"to":[25,98,112,130],"add":[26],"punctuation":[27,38,72,90,151],"marks":[28],"in":[29,75],"these":[30,50],"transcripts.":[31],"Most":[32],"state-of-the-art":[33],"improve":[34],"performance":[36,74,145],"of":[37,84,116],"restoration":[39,73,91,152],"models":[40,51],"by":[41],"incorporating":[42],"external":[43],"information,":[44],"such":[45],"as":[46],"part-of-speech(POS)":[47],"tags.":[48],"Although":[49],"take":[52],"POS":[53,69,85,100],"tags":[54,70,86,101],"into":[55],"account,":[56],"they":[57],"predominantly":[58],"focus":[59],"on":[60,87],"English":[62],"language,":[63],"with":[64,102],"limited":[65],"research":[66],"examining":[67],"how":[68],"Chinese.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,107,123],"validate":[81],"effectiveness":[83,115,149],"Chinese":[89,122,127],"task,":[92],"develop":[94,124],"an":[95],"innovative":[96],"method":[97,141],"fusing":[99],"contextual":[103],"embeddings.":[104],"For":[105],"English,":[106],"use":[108],"IWSLT":[110],"dataset":[111,129],"verify":[113],"fusion":[118],"approach,":[119],"while":[120],"a":[125],"new":[126],"evaluate":[131],"proposed":[133,140],"methods.":[134],"Experimental":[135],"results":[136],"show":[137],"that":[138],"our":[139],"can":[142],"consistently":[143],"obtain":[144],"gains,":[146],"indicating":[147],"its":[148],"tasks.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}