{"id":"https://openalex.org/W4398794856","doi":"https://doi.org/10.1145/3795686","title":"A Survey on Recent Advances in Conversational Data Generation","display_name":"A Survey on Recent Advances in Conversational Data Generation","publication_year":2026,"publication_date":"2026-02-19","ids":{"openalex":"https://openalex.org/W4398794856","doi":"https://doi.org/10.1145/3795686"},"language":"en","primary_location":{"id":"doi:10.1145/3795686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795686","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3795686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067650300","display_name":"Heydar Soudani","orcid":"https://orcid.org/0000-0003-0393-8662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heydar Soudani","raw_affiliation_strings":["Radboud Universiteit"],"raw_orcid":"https://orcid.org/0000-0003-0393-8662","affiliations":[{"raw_affiliation_string":"Radboud Universiteit","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093967424","display_name":"Roxana Petcu","orcid":"https://orcid.org/0000-0002-2617-205X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Roxana Petcu","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-2617-205X","affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-8312-0694","affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047151593","display_name":"Faegheh Hasibi","orcid":"https://orcid.org/0009-0006-9986-482X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faegheh Hasibi","raw_affiliation_strings":["Radboud Universiteit"],"raw_orcid":"https://orcid.org/0009-0006-9986-482X","affiliations":[{"raw_affiliation_string":"Radboud Universiteit","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00245714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"58","issue":"10","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8485000133514404,"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":0.8485000133514404,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7350999712944031,"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/T12128","display_name":"AI in Service Interactions","score":0.707099974155426,"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":0.44244521856307983},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42297476530075073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44244521856307983},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42297476530075073}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3795686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795686","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2405.13003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13003","pdf_url":"https://arxiv.org/pdf/2405.13003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arXiv.org:2405.13003","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2405.13003","pdf_url":"https://arxiv.org/pdf/2405.13003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/331869","is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/331869","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/331869/331869.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"},{"id":"doi:10.48550/arxiv.2405.13003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.13003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3795686","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795686","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W4226059645","https://openalex.org/W2949849869","https://openalex.org/W4411119806","https://openalex.org/W4399631598","https://openalex.org/W4389520244","https://openalex.org/W2944069152","https://openalex.org/W2913443447","https://openalex.org/W4289529514","https://openalex.org/W2950970512","https://openalex.org/W4205243614","https://openalex.org/W3155952370","https://openalex.org/W4404534210","https://openalex.org/W4404783559","https://openalex.org/W3173658292","https://openalex.org/W2963206148","https://openalex.org/W4385574182","https://openalex.org/W4404781717","https://openalex.org/W2137496706","https://openalex.org/W3205525806","https://openalex.org/W3161207330","https://openalex.org/W3015834167","https://openalex.org/W2997771882","https://openalex.org/W2964223283","https://openalex.org/W4285206788","https://openalex.org/W4392487838","https://openalex.org/W2950299257","https://openalex.org/W3177075735","https://openalex.org/W4409218928","https://openalex.org/W4385574338","https://openalex.org/W4236521339","https://openalex.org/W4389009366","https://openalex.org/W3103291112","https://openalex.org/W3099231098","https://openalex.org/W4385794172"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,41,156,189],"conversational":[3,28,67,91,151],"systems":[4,16],"have":[5],"significantly":[6],"enhanced":[7],"human-machine":[8],"interactions":[9],"across":[10],"various":[11],"domains.":[12],"However,":[13],"training":[14],"these":[15],"is":[17,168],"challenging":[18],"due":[19],"to":[20,58,76,169,186],"the":[21,48,108,132,143,157],"scarcity":[22],"of":[23,50,89,98,135,180],"specialized":[24],"dialogue":[25,52,99],"data.":[26],"Traditionally,":[27],"datasets":[29,61],"were":[30],"created":[31],"through":[32],"crowdsourcing,":[33],"but":[34],"this":[35,80,190],"method":[36],"has":[37,54],"proven":[38],"costly,":[39],"limited":[40],"scale,":[42],"and":[43,73,86,104,121,125,146,159,174,183],"labor-intensive.":[44],"As":[45],"a":[46,70,84,127],"solution,":[47],"development":[49],"synthetic":[51,150],"data":[53,92,117,137],"emerged,":[55],"utilizing":[56],"techniques":[57],"augment":[59],"existing":[60,109],"or":[62],"convert":[63],"textual":[64],"resources":[65],"into":[66],"formats,":[68],"providing":[69],"more":[71],"efficient":[72],"scalable":[74],"approach":[75],"dataset":[77],"creation.":[78],"In":[79],"survey,":[81],"we":[82,141],"offer":[83],"systematic":[85],"comprehensive":[87],"review":[88],"multi-turn":[90],"generation,":[93,120],"focusing":[94],"on":[95,112],"three":[96],"types":[97],"systems:":[100],"open":[101],"domain,":[102],"task-oriented,":[103],"information-seeking.":[105],"We":[106],"categorize":[107],"research":[110,188],"based":[111],"key":[113],"components":[114],"like":[115],"seed":[116],"creation,":[118],"utterance":[119],"quality":[122],"filtering":[123],"methods,":[124],"introduce":[126],"general":[128],"framework":[129],"that":[130],"outlines":[131],"main":[133],"principles":[134],"conversation":[136],"generation":[138],"systems.":[139],"Additionally,":[140],"examine":[142],"evaluation":[144],"metrics":[145],"methods":[147,182],"for":[148,163,172],"assessing":[149],"data,":[152],"address":[153],"current":[154],"challenges":[155],"field,":[158],"explore":[160],"potential":[161],"directions":[162],"future":[164],"research.":[165],"Our":[166],"goal":[167],"accelerate":[170],"progress":[171],"researchers":[173],"practitioners":[175],"by":[176],"presenting":[177],"an":[178],"overview":[179],"state-of-the-art":[181],"highlighting":[184],"opportunities":[185],"further":[187],"area.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2024-05-25T00:00:00"}