{"id":"https://openalex.org/W4375869146","doi":"https://doi.org/10.1109/icassp49357.2023.10096298","title":"Improving Disfluency Detection with Multi-Scale Self Attention and Contrastive Learning","display_name":"Improving Disfluency Detection with Multi-Scale Self Attention and Contrastive Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869146","doi":"https://doi.org/10.1109/icassp49357.2023.10096298"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5039641921","display_name":"Peiying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peiying Wang","raw_affiliation_strings":["JD AI,Beijing,China","JD AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072003801","display_name":"Chaoqun Duan","orcid":"https://orcid.org/0000-0002-8938-5474"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqun Duan","raw_affiliation_strings":["JD AI,Beijing,China","JD AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633086","display_name":"Chen Meng","orcid":"https://orcid.org/0000-0002-5875-1400"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Chen","raw_affiliation_strings":["JD AI,Beijing,China","JD AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI,Beijing,China","JD AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039641921"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":1.9606,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87470707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9933000206947327,"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":0.9907000064849854,"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":0.8357874155044556},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6525530815124512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6322038769721985},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6053516864776611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5638691186904907},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5302402973175049},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.49918413162231445},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.48781946301460266},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4843827188014984},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.47905266284942627},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4757378101348877},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4514722228050232},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42489826679229736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4162946343421936},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.4127460718154907},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.13683325052261353},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1294187307357788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09751597046852112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357874155044556},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6525530815124512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6322038769721985},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6053516864776611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638691186904907},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5302402973175049},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.49918413162231445},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.48781946301460266},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4843827188014984},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.47905266284942627},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4757378101348877},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4514722228050232},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42489826679229736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4162946343421936},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.4127460718154907},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.13683325052261353},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1294187307357788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09751597046852112},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2021208044","https://openalex.org/W2147880316","https://openalex.org/W2166637769","https://openalex.org/W2293765256","https://openalex.org/W2406344726","https://openalex.org/W2604693796","https://openalex.org/W2741045570","https://openalex.org/W2756923881","https://openalex.org/W2889320445","https://openalex.org/W2895705233","https://openalex.org/W2896457183","https://openalex.org/W2901791227","https://openalex.org/W2908510526","https://openalex.org/W2962902328","https://openalex.org/W2963729456","https://openalex.org/W2970682957","https://openalex.org/W2996428491","https://openalex.org/W2996888978","https://openalex.org/W3100480949","https://openalex.org/W3156636935","https://openalex.org/W3184998487","https://openalex.org/W3201888710","https://openalex.org/W4287824654","https://openalex.org/W6682082992","https://openalex.org/W6741936628","https://openalex.org/W6754755230","https://openalex.org/W6755207826","https://openalex.org/W6756949633","https://openalex.org/W6757817989","https://openalex.org/W6768021236","https://openalex.org/W6771917389","https://openalex.org/W6802169743","https://openalex.org/W7038994942"],"related_works":["https://openalex.org/W2064245876","https://openalex.org/W2049493498","https://openalex.org/W4390911461","https://openalex.org/W1551498276","https://openalex.org/W2952664794","https://openalex.org/W4288558800","https://openalex.org/W2953770453","https://openalex.org/W3032655135","https://openalex.org/W2534732449","https://openalex.org/W4387885913"],"abstract_inverted_index":{"Disfluency":[0],"detection":[1],"aims":[2],"to":[3,16,23,34,56,94,117,128],"recognize":[4],"disfluencies":[5,31],"in":[6,137],"sentences.":[7],"Existing":[8],"works":[9],"usually":[10],"adopt":[11],"a":[12,74,143],"sequence":[13],"labeling":[14],"model":[15,127],"tackle":[17],"this":[18,86],"task.":[19,87],"They":[20],"also":[21],"attempt":[22],"integrate":[24],"into":[25],"models":[26],"the":[27,30,35,38,89,111,115,119,126,130,135,168],"feature":[28],"that":[29,164],"are":[32,54],"similar":[33],"correct":[36],"phrase,":[37],"so-called":[39],"\"rough":[40],"copy\".":[41],"However,":[42],"they":[43],"heavily":[44],"rely":[45],"on":[46,142,174],"hand-craft":[47],"features":[48],"or":[49],"word-to-word":[50],"match":[51],"patterns,":[52],"which":[53,154],"insufficient":[55],"precisely":[57],"capture":[58],"such":[59],"rough":[60],"copy":[61],"and":[62,65,79,102,121,124,148,170],"cause":[63],"under-tagging":[64],"over-tagging":[66],"problems.":[67],"To":[68],"alleviate":[69],"these":[70],"problems,":[71],"we":[72],"propose":[73],"multi-scale":[75],"self-attention":[76],"mechanism":[77],"(MSAT)":[78],"design":[80],"contrastive":[81],"learning":[82],"(CL)":[83],"loss":[84],"for":[85,97],"Specifically,":[88],"MSAT":[90],"leverages":[91],"token":[92],"representations":[93,96],"learn":[95],"different":[98],"scales":[99],"of":[100,114],"phrases,":[101],"then":[103],"compute":[104],"similarity":[105],"among":[106],"them.":[107],"The":[108],"CL":[109],"adopts":[110],"fluent":[112,131],"version":[113,132],"input":[116,136],"build":[118],"positive":[120],"negative":[122],"samples":[123],"encourages":[125],"keep":[129],"consistent":[133],"with":[134],"semantics.":[138],"We":[139],"conduct":[140],"experiments":[141],"public":[144],"English":[145],"dataset":[146,152],"Switchboard,":[147],"an":[149,158],"in-house":[150],"Chinese":[151],"Waihu,":[153],"is":[155],"derived":[156],"from":[157],"online":[159],"conversation":[160],"bot.":[161],"Results":[162],"show":[163],"our":[165],"method":[166],"outperforms":[167],"baselines":[169],"achieves":[171],"superior":[172],"performance":[173],"both":[175],"datasets.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}