{"id":"https://openalex.org/W4281384017","doi":"https://doi.org/10.1109/cscwd54268.2022.9776017","title":"Making Punctuation Restoration Robust with Disfluency Detection","display_name":"Making Punctuation Restoration Robust with Disfluency Detection","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4281384017","doi":"https://doi.org/10.1109/cscwd54268.2022.9776017"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd54268.2022.9776017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd54268.2022.9776017","pdf_url":null,"source":{"id":"https://openalex.org/S4363607909","display_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5100392097","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0000-5702-3009"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112116986","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0001-6005-5714"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003873405","display_name":"Wen Jiang","orcid":"https://orcid.org/0000-0001-5793-4363"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Jiang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102791450","display_name":"Yihui Ren","orcid":"https://orcid.org/0009-0008-8620-8481"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Ren","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5061,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6179011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"395","last_page":"399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9141298532485962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816112756729126},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8003539443016052},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6626747250556946},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5417933464050293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5184299945831299},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5144813060760498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5061866641044617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49362075328826904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47006091475486755},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4229905903339386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12763985991477966},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0843290388584137}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9141298532485962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816112756729126},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8003539443016052},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6626747250556946},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5417933464050293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5184299945831299},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5144813060760498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5061866641044617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49362075328826904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47006091475486755},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4229905903339386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12763985991477966},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0843290388584137},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd54268.2022.9776017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd54268.2022.9776017","pdf_url":null,"source":{"id":"https://openalex.org/S4363607909","display_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W26608090","https://openalex.org/W94670513","https://openalex.org/W2166116787","https://openalex.org/W2166128510","https://openalex.org/W2398104528","https://openalex.org/W2403334028","https://openalex.org/W2575282817","https://openalex.org/W2705373224","https://openalex.org/W2757416441","https://openalex.org/W2896457183","https://openalex.org/W2937170468","https://openalex.org/W3011222885","https://openalex.org/W3016128928","https://openalex.org/W3037101098","https://openalex.org/W3096718507","https://openalex.org/W3097077634","https://openalex.org/W3106905592","https://openalex.org/W3160648428","https://openalex.org/W3196445330","https://openalex.org/W3210052536","https://openalex.org/W4287824654","https://openalex.org/W6601052561","https://openalex.org/W6603793917","https://openalex.org/W6684467545","https://openalex.org/W6684662674","https://openalex.org/W6731992975","https://openalex.org/W6755207826","https://openalex.org/W6771917389"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W3110264473","https://openalex.org/W4254960163","https://openalex.org/W2936002343","https://openalex.org/W4293202849","https://openalex.org/W4315704968","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2188883480","https://openalex.org/W2972807713"],"abstract_inverted_index":{"Transcripts":[0],"generated":[1],"by":[2,13,34],"automatic":[3,27,78],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7],"usually":[8],"have":[9,30],"poor":[10],"readability":[11],"caused":[12],"lacking":[14],"of":[15,22,44],"punctuation":[16,28,79,104],"and":[17,52,61,74,91,102,123],"containing":[18],"a":[19,56],"large":[20,36,42],"portion":[21],"dis-fluency.":[23],"Existing":[24],"methods":[25],"for":[26,77],"restoration":[29],"obtain":[31],"great":[32],"improvements":[33],"finetuning":[35,53],"pre-trained":[37],"language":[38,47],"models":[39],"(LMs).":[40],"However,":[41],"amount":[43],"well-formatted":[45],"written":[46],"are":[48],"used":[49],"in":[50],"pre-training":[51],"LMs,":[54],"leaving":[55],"mismatch":[57],"between":[58],"the":[59,68,87,92,115,119],"training":[60,89],"application.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"modify":[67],"ELECTRA":[69],"model":[70],"with":[71],"disfluency":[72,85,98],"generator":[73,82,100],"multi-task":[75],"discriminator":[76,93],"restoration.":[80],"The":[81],"dynamically":[83],"inject":[84],"into":[86],"input":[88],"data,":[90],"is":[94],"trained":[95],"to":[96],"distinguish":[97],"from":[99],"outputs":[101],"predict":[103],"marks.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"that":[109],"our":[110,124],"proposed":[111],"method":[112],"significantly":[113],"outperforms":[114],"baselines":[116],"based":[117],"on":[118],"English":[120],"IWSLT":[121],"dataset":[122],"newly":[125],"collected":[126],"Chinese":[127],"dataset.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}