{"id":"https://openalex.org/W7168397752","doi":"https://doi.org/10.48448/f9mk-by83","title":"Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models","display_name":"Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7168397752","doi":"https://doi.org/10.48448/f9mk-by83"},"language":"en","primary_location":{"id":"doi:10.48448/f9mk-by83","doi":"https://doi.org/10.48448/f9mk-by83","is_oa":true,"landing_page_url":"https://doi.org/10.48448/f9mk-by83","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/f9mk-by83","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140798803","display_name":"Association for Computational Linguistics 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064912341","display_name":"Hendrik Buschmeier","orcid":"https://orcid.org/0000-0002-9613-5713","observed_orcids":["https://orcid.org/0000-0002-9613-5713"]},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Buschmeier, Hendrik","raw_affiliation_strings":["Bielefeld University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bielefeld University","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140924602","display_name":"Langchu Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Langchu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027595160","display_name":"Leyi Lao","orcid":"https://orcid.org/0009-0004-7583-9879","observed_orcids":["https://orcid.org/0009-0004-7583-9879"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lao, Leyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091225228","display_name":"Gabriel Skantze","orcid":"https://orcid.org/0000-0002-8579-1790","observed_orcids":["https://orcid.org/0000-0002-8579-1790"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Skantze, Gabriel","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140768618","display_name":"Yu Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140780275","display_name":"Yang Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9937000274658203,"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/T12031","display_name":"Speech and dialogue systems","score":0.9937000274658203,"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":0.0024999999441206455,"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":0.0020000000949949026,"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/backchannels","display_name":"backchannels","score":0.9929999709129333},{"id":"https://openalex.org/keywords/fillers","display_name":"fillers","score":0.8949999809265137},{"id":"https://openalex.org/keywords/dialogue-representation","display_name":"dialogue representation","score":0.6460000276565552},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/dialogue-corpus","display_name":"dialogue corpus","score":0.8209999799728394},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.5860000252723694},{"id":"https://openalex.org/keywords/silhouette-score","display_name":"silhouette coefficient","score":0.6620000004768372},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"natural language generation","score":0.8899999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269999980926514},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6793000102043152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6565999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.39719998836517334},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/f9mk-by83","doi":"https://doi.org/10.48448/f9mk-by83","is_oa":true,"landing_page_url":"https://doi.org/10.48448/f9mk-by83","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/f9mk-by83","doi":"https://doi.org/10.48448/f9mk-by83","is_oa":true,"landing_page_url":"https://doi.org/10.48448/f9mk-by83","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155035277","https://openalex.org/W7214334731","https://openalex.org/W4415348475","https://openalex.org/W4392902922","https://openalex.org/W17761477","https://openalex.org/W3087841754","https://openalex.org/W4364385674","https://openalex.org/W258837700","https://openalex.org/W3024131638","https://openalex.org/W6929029244"],"abstract_inverted_index":{"Backchannels":[0],"and":[1,46,50,54,77,79,105,116],"fillers":[2,51],"are":[3,38,52,147],"important":[4],"linguistic":[5],"expressions":[6],"in":[7,17,29,44,85,102],"dialogue,":[8],"but":[9],"often":[10],"treated":[11],"as":[12],"\"noise\"":[13],"to":[14,56,71,96,119],"be":[15],"bypassed":[16],"modern":[18],"transformer-based":[19],"language":[20,30,112,127],"models.":[21],"Our":[22,134],"work":[23],"studies":[24],"the":[25,72,98,122,137],"representation":[26,74],"of":[27,75,139,150],"them":[28],"models":[31,37,128],"using":[32],"three":[33,41],"fine-tuning":[34,59,93],"strategies.":[35],"The":[36],"trained":[39],"on":[40],"dialogue":[42],"corpora":[43],"English":[45],"Japanese,":[47],"where":[48],"backchannels":[49,76],"preserved":[53],"annotated,":[55],"investigate":[57],"how":[58],"can":[60],"help":[61],"LMs":[62,95,142,145],"learn":[63],"their":[64],"representations.":[65],"We":[66,108],"first":[67],"apply":[68],"clustering":[69],"analysis":[70,118],"learnt":[73],"fillers,":[78],"have":[80],"found":[81],"increased":[82],"silhouette":[83],"scores":[84],"representations":[86],"from":[87],"fine-tuned":[88,126],"models,":[89],"which":[90],"suggests":[91],"that":[92,121,146],"enables":[94],"distinguish":[97],"nuanced":[99],"semantic":[100],"variation":[101],"different":[103],"backchannel":[104],"filler":[106],"use.":[107],"also":[109],"use":[110],"natural":[111],"generation":[113],"(NLG)":[114],"metrics":[115],"qualitative":[117],"confirm":[120],"utterances":[123,131],"generated":[124],"by":[125],"resemble":[129],"human-produced":[130],"more":[132,148],"closely.":[133],"findings":[135],"suggest":[136],"potentials":[138],"transforming":[140],"general":[141],"into":[143],"conversational":[144],"capable":[149],"producing":[151],"human-like":[152],"languages":[153],"adequately.":[154]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-16T00:00:00"}