{"id":"https://openalex.org/W4200184345","doi":"https://doi.org/10.1145/3487290","title":"Combining Self-supervised Learning and Active Learning for Disfluency Detection","display_name":"Combining Self-supervised Learning and Active Learning for Disfluency Detection","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4200184345","doi":"https://doi.org/10.1145/3487290"},"language":"en","primary_location":{"id":"doi:10.1145/3487290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3487290","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5070059389","display_name":"Shaolei Wang","orcid":"https://orcid.org/0000-0002-0691-9179"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaolei Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, HeiLongJiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, HeiLongJiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, HeiLongJiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, HeiLongJiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, HeiLongJiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, HeiLongJiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067025788","display_name":"Sendong Zhao","orcid":"https://orcid.org/0000-0002-4676-1812"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sendong Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, HeiLongJiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, HeiLongJiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418156","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0002-9091-7757"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, HeiLongJiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, HeiLongJiang, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070059389"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76525913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"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":0.9954000115394592,"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":0.8218680620193481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6332709789276123},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5319811105728149},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5254815220832825},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5021681785583496},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.493247926235199},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4803532361984253},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44313159584999084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41888168454170227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39488738775253296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34429532289505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218680620193481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6332709789276123},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5319811105728149},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5254815220832825},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5021681785583496},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.493247926235199},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4803532361984253},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44313159584999084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41888168454170227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39488738775253296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34429532289505005},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3487290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3487290","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G2598032351","display_name":null,"funder_award_id":"61976072 and 61772153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5774293737","display_name":null,"funder_award_id":"2020AAA0106501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W1520997877","https://openalex.org/W2021208044","https://openalex.org/W2085989833","https://openalex.org/W2169058332","https://openalex.org/W2203858612","https://openalex.org/W2214962597","https://openalex.org/W2250441574","https://openalex.org/W2250861254","https://openalex.org/W2293765256","https://openalex.org/W2400986993","https://openalex.org/W2406344726","https://openalex.org/W2418403507","https://openalex.org/W2462831000","https://openalex.org/W2550462002","https://openalex.org/W2566299766","https://openalex.org/W2592170186","https://openalex.org/W2741045570","https://openalex.org/W2756923881","https://openalex.org/W2785787385","https://openalex.org/W2896457183","https://openalex.org/W2899181341","https://openalex.org/W2901791227","https://openalex.org/W2903158431","https://openalex.org/W2904571617","https://openalex.org/W2911333381","https://openalex.org/W2937176889","https://openalex.org/W2962731964","https://openalex.org/W2962739339","https://openalex.org/W2963505445","https://openalex.org/W2963729456","https://openalex.org/W2964172015","https://openalex.org/W2964282813","https://openalex.org/W2970043232","https://openalex.org/W2972328063","https://openalex.org/W2996888978","https://openalex.org/W2998704965","https://openalex.org/W3012546161","https://openalex.org/W3034323214","https://openalex.org/W3100509098","https://openalex.org/W3101889167","https://openalex.org/W3102685326","https://openalex.org/W3105522431","https://openalex.org/W6758759751","https://openalex.org/W6767808968"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W1998701884"],"abstract_inverted_index":{"Spoken":[0],"language":[1,8],"is":[2,31,55,145,204,277],"fundamentally":[3],"different":[4],"from":[5,98,125],"the":[6,24,35,65,113,185,200,211,216,226,234,246,255,288,294],"written":[7],"in":[9,39,61,69,183],"that":[10,20,184,267],"it":[11],"contains":[12],"frequent":[13],"disfluencies":[14],"or":[15,95],"parts":[16],"of":[17,257,287,304],"an":[18],"utterance":[19],"are":[21,189],"corrected":[22],"by":[23,92,229,244,268],"speaker.":[25],"Disfluency":[26],"detection":[27,48,151,164],"(removing":[28],"these":[29,132],"disfluencies)":[30],"desirable":[32],"to":[33,46,59,111,121,135,177,210,224,240,250,279],"clean":[34],"input":[36],"for":[37,75,82,162],"use":[38],"downstream":[40],"NLP":[41],"tasks.":[42],"Most":[43],"existing":[44],"approaches":[45],"disfluency":[47,83,150,163,201],"heavily":[49],"rely":[50],"on":[51,171,192,215,292],"human-annotated":[52,149],"data,":[53],"which":[54],"scarce":[56],"and":[57,79,101,117,165,195,252,301],"expensive":[58],"obtain":[60],"practice.":[62],"To":[63],"tackle":[64],"training":[66,90,152,187,218,290],"data":[67,91,100,188,291],"bottleneck,":[68],"this":[70],"work,":[71],"we":[72,86],"investigate":[73],"methods":[74],"combining":[76,269],"self-supervised":[77,104,155,258,270],"learning":[78,81,156,232,238,259,271],"active":[80,231,273],"detection.":[84],"First,":[85],"construct":[87],"large-scale":[88],"pseudo":[89,186],"randomly":[93],"adding":[94],"deleting":[96],"words":[97,116],"unlabeled":[99],"propose":[102],"two":[103,133],"pre-training":[105],"tasks:":[106],"(i)":[107],"a":[108,138,172,206,261,302],"tagging":[109],"task":[110],"detect":[112],"added":[114],"noisy":[115],"(ii)":[118],"sentence":[119],"classification":[120],"distinguish":[122],"original":[123,289],"sentences":[124],"grammatically":[126],"incorrect":[127],"sentences.":[128],"We":[129,220,265],"then":[130,146],"combine":[131],"tasks":[134],"jointly":[136],"pre-train":[137],"neural":[139,143],"network.":[140],"The":[141,154],"pre-trained":[142],"network":[144],"fine-tuned":[147],"using":[148],"data.":[153,308],"method":[157],"can":[158,253],"capture":[159],"task-special":[160],"knowledge":[161],"achieve":[166],"better":[167],"performance":[168,207,227,282],"when":[169],"fine-tuning":[170,235],"small":[173,262],"annotated":[174,263,306],"dataset":[175],"compared":[176,209],"other":[178],"supervised":[179,212],"methods.":[180],"However,":[181],"limited":[182],"generated":[190],"based":[191],"simple":[193],"heuristics":[194],"cannot":[196],"fully":[197],"cover":[198],"all":[199],"patterns,":[202],"there":[203],"still":[205],"gap":[208,228],"models":[213],"trained":[214],"full":[217],"dataset.":[219,264],"further":[221],"explore":[222],"how":[223],"bridge":[225],"integrating":[230],"during":[233],"process.":[236],"Active":[237],"strives":[239],"reduce":[241],"annotation":[242],"costs":[243],"choosing":[245],"most":[247],"critical":[248],"examples":[249],"label":[251],"address":[254],"weakness":[256],"with":[260,272,283],"show":[266],"learning,":[274],"our":[275],"model":[276],"able":[278],"match":[280],"state-of-the-art":[281],"just":[284],"about":[285],"10%":[286],"both":[293],"commonly":[295],"used":[296],"English":[297],"Switchboard":[298],"test":[299],"set":[300,303],"in-house":[305],"Chinese":[307]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}