{"id":"https://openalex.org/W4402986326","doi":"https://doi.org/10.1162/coli_a_00540","title":"Evaluating Synthetic Data Generation from User Generated Text","display_name":"Evaluating Synthetic Data Generation from User Generated Text","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4402986326","doi":"https://doi.org/10.1162/coli_a_00540"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00540","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00540","pdf_url":"https://direct.mit.edu/coli/article-pdf/51/1/191/2481447/coli_a_00540.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/51/1/191/2481447/coli_a_00540.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050362710","display_name":"Jenny Chim","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jenny Chim","raw_affiliation_strings":["Queen Mary University of London, School of Electronic Engineering, and Computer Science. c.chim@qmul.ac.uk","Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, School of Electronic Engineering, and Computer Science. c.chim@qmul.ac.uk","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021442709","display_name":"Julia Ive","orcid":"https://orcid.org/0000-0002-3931-3392"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julia Ive","raw_affiliation_strings":["Queen Mary University of London, School of Electronic Engineering, and Computer Science. j.ive@qmul.ac.uk","Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, School of Electronic Engineering, and Computer Science. j.ive@qmul.ac.uk","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007426895","display_name":"Maria Liakata","orcid":"https://orcid.org/0000-0001-5765-0416"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria Liakata","raw_affiliation_strings":["Queen Mary University of London / The Alan Turing Institute, School of Electronic Engineering and Computer Science. m.liakata@qmul.ac.uk","Queen Mary University of London / The Alan Turing Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London / The Alan Turing Institute, School of Electronic Engineering and Computer Science. m.liakata@qmul.ac.uk","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London / The Alan Turing Institute","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0916,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88572638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"51","issue":"1","first_page":"191","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9864000082015991,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9864000082015991,"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/T11719","display_name":"Data Quality and Management","score":0.9297000169754028,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9269999861717224,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.751203179359436},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.46538180112838745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43223845958709717},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42238131165504456},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3442772328853607},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.320920467376709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751203179359436},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.46538180112838745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43223845958709717},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42238131165504456},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3442772328853607},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.320920467376709}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00540","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00540","pdf_url":"https://direct.mit.edu/coli/article-pdf/51/1/191/2481447/coli_a_00540.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:33fda39eab614703954da10ff66758c6","is_oa":true,"landing_page_url":"https://doaj.org/article/33fda39eab614703954da10ff66758c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics (2024)","raw_type":"article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/103483","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/103483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00540","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00540","pdf_url":"https://direct.mit.edu/coli/article-pdf/51/1/191/2481447/coli_a_00540.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G135677151","display_name":null,"funder_award_id":"V030302/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3321750416","display_name":"AI UK: Creating an International Ecosystem for Responsible AI Research and Innovation","funder_award_id":"EP/Y009800/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3881378079","display_name":null,"funder_award_id":"EP/Y009800/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G4088380979","display_name":null,"funder_award_id":"EP/V030302/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7399830500","display_name":null,"funder_award_id":"EP/V030302/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8581904048","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G905227802","display_name":null,"funder_award_id":"EP/Y009800/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402986326.pdf","grobid_xml":"https://content.openalex.org/works/W4402986326.grobid-xml"},"referenced_works_count":185,"referenced_works":["https://openalex.org/W1125436246","https://openalex.org/W1757621696","https://openalex.org/W1796112755","https://openalex.org/W1913627016","https://openalex.org/W1964642694","https://openalex.org/W1970381522","https://openalex.org/W1972820248","https://openalex.org/W1985610876","https://openalex.org/W1995814612","https://openalex.org/W1997865285","https://openalex.org/W2013568550","https://openalex.org/W2033922434","https://openalex.org/W2083773633","https://openalex.org/W2086040578","https://openalex.org/W2092475127","https://openalex.org/W2101105183","https://openalex.org/W2104933073","https://openalex.org/W2106111649","https://openalex.org/W2110158442","https://openalex.org/W2113452810","https://openalex.org/W2136487259","https://openalex.org/W2152198378","https://openalex.org/W2153344843","https://openalex.org/W2159024459","https://openalex.org/W2166434810","https://openalex.org/W2166637769","https://openalex.org/W2250342921","https://openalex.org/W2264788300","https://openalex.org/W2295585256","https://openalex.org/W2539350388","https://openalex.org/W2563852449","https://openalex.org/W2566069120","https://openalex.org/W2567639685","https://openalex.org/W2593481629","https://openalex.org/W2623779865","https://openalex.org/W2740201240","https://openalex.org/W2751687090","https://openalex.org/W2806532810","https://openalex.org/W2889316516","https://openalex.org/W2891161640","https://openalex.org/W2916772188","https://openalex.org/W2949678053","https://openalex.org/W2949849869","https://openalex.org/W2950866572","https://openalex.org/W2951476960","https://openalex.org/W2962753250","https://openalex.org/W2963036876","https://openalex.org/W2963456134","https://openalex.org/W2963572446","https://openalex.org/W2963737810","https://openalex.org/W2963825865","https://openalex.org/W2963903950","https://openalex.org/W2963913356","https://openalex.org/W2964235839","https://openalex.org/W2966735522","https://openalex.org/W2971086334","https://openalex.org/W2991319004","https://openalex.org/W2995465878","https://openalex.org/W2997616454","https://openalex.org/W3000779003","https://openalex.org/W3014648098","https://openalex.org/W3023553115","https://openalex.org/W3024357968","https://openalex.org/W3034383590","https://openalex.org/W3035252911","https://openalex.org/W3035377849","https://openalex.org/W3037669018","https://openalex.org/W3037831233","https://openalex.org/W3081783897","https://openalex.org/W3100727892","https://openalex.org/W3103639864","https://openalex.org/W3103649165","https://openalex.org/W3105556263","https://openalex.org/W3153451655","https://openalex.org/W3156636935","https://openalex.org/W3161838540","https://openalex.org/W3169754167","https://openalex.org/W3174073137","https://openalex.org/W3174361803","https://openalex.org/W3174685870","https://openalex.org/W3174724858","https://openalex.org/W3175115403","https://openalex.org/W3177765786","https://openalex.org/W3186655327","https://openalex.org/W3191847389","https://openalex.org/W3196248941","https://openalex.org/W3197685490","https://openalex.org/W3198995825","https://openalex.org/W3199834251","https://openalex.org/W3200503965","https://openalex.org/W3200514611","https://openalex.org/W3201300710","https://openalex.org/W3207531498","https://openalex.org/W3207604732","https://openalex.org/W3211466672","https://openalex.org/W3213241618","https://openalex.org/W3214222557","https://openalex.org/W3214380581","https://openalex.org/W4200629072","https://openalex.org/W4205477024","https://openalex.org/W4205619213","https://openalex.org/W4205741916","https://openalex.org/W4206031910","https://openalex.org/W4221152824","https://openalex.org/W4230541727","https://openalex.org/W4285236768","https://openalex.org/W4285265395","https://openalex.org/W4287120901","https://openalex.org/W4287829148","https://openalex.org/W4296711106","https://openalex.org/W4307475457","https://openalex.org/W4307955997","https://openalex.org/W4309674289","https://openalex.org/W4313035869","https://openalex.org/W4327656064","https://openalex.org/W4363676096","https://openalex.org/W4367365616","https://openalex.org/W4378189609","https://openalex.org/W4381432831","https://openalex.org/W4385565597","https://openalex.org/W4385570594","https://openalex.org/W4385570960","https://openalex.org/W4385571142","https://openalex.org/W4385571220","https://openalex.org/W4385572039","https://openalex.org/W4385572805","https://openalex.org/W4385573108","https://openalex.org/W4385573325","https://openalex.org/W4385573981","https://openalex.org/W4385574220","https://openalex.org/W4386566523","https://openalex.org/W4386566623","https://openalex.org/W4388218284","https://openalex.org/W4389519059","https://openalex.org/W4389520377","https://openalex.org/W4389521054","https://openalex.org/W4389523957","https://openalex.org/W4389636360","https://openalex.org/W4399362834","https://openalex.org/W4412273007","https://openalex.org/W6632455782","https://openalex.org/W6675054812","https://openalex.org/W6676670208","https://openalex.org/W6678262379","https://openalex.org/W6679663036","https://openalex.org/W6681703963","https://openalex.org/W6682578559","https://openalex.org/W6691077208","https://openalex.org/W6693381558","https://openalex.org/W6721933647","https://openalex.org/W6732197452","https://openalex.org/W6735926176","https://openalex.org/W6739834160","https://openalex.org/W6741121127","https://openalex.org/W6743924987","https://openalex.org/W6744282078","https://openalex.org/W6748184129","https://openalex.org/W6748237992","https://openalex.org/W6763701032","https://openalex.org/W6765779288","https://openalex.org/W6765861705","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6778883912","https://openalex.org/W6787335730","https://openalex.org/W6790840731","https://openalex.org/W6791024018","https://openalex.org/W6797489503","https://openalex.org/W6838900328","https://openalex.org/W6839193947","https://openalex.org/W6844053373","https://openalex.org/W6850216576","https://openalex.org/W6851152545","https://openalex.org/W6852927592","https://openalex.org/W6853006944","https://openalex.org/W6853773940","https://openalex.org/W6853794594","https://openalex.org/W6854004153","https://openalex.org/W6854866820","https://openalex.org/W6856529530","https://openalex.org/W6856565980","https://openalex.org/W6857318322","https://openalex.org/W6860710830","https://openalex.org/W6861183265","https://openalex.org/W6869145442"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4389009515","https://openalex.org/W3194553618","https://openalex.org/W3211013666","https://openalex.org/W4366557471","https://openalex.org/W3169121507","https://openalex.org/W4213212078","https://openalex.org/W4247507802","https://openalex.org/W2122804826","https://openalex.org/W2138640103"],"abstract_inverted_index":{"Abstract":[0],"User-generated":[1],"content":[2],"provides":[3],"a":[4,62,78,91],"rich":[5],"resource":[6],"to":[7,49,86,138],"study":[8],"social":[9],"and":[10,26,75,96,99,119,145],"behavioral":[11],"phenomena.":[12],"Although":[13],"its":[14],"application":[15],"potential":[16],"is":[17,127],"currently":[18],"limited":[19],"by":[20],"the":[21,27,105,108,128,139],"paucity":[22],"of":[23,64,93,111],"expert":[24],"labels":[25],"privacy":[28],"risks":[29],"inherent":[30],"in":[31,136],"personal":[32],"data,":[33],"synthetic":[34,53,112,157],"data":[35,55,68],"can":[36],"help":[37],"mitigate":[38],"this":[39,42],"bottleneck.":[40],"In":[41],"work,":[43],"we":[44,103],"introduce":[45,83],"an":[46],"evaluation":[47,131],"framework":[48,132],"facilitate":[50,152],"research":[51],"on":[52],"language":[54,158],"generation":[56,94,116],"for":[57,66,80,133],"user-generated":[58,134],"text.":[59],"We":[60,82,148],"define":[61],"set":[63,92],"aspects":[65,110],"assessing":[67],"quality,":[69],"namely,":[70],"style":[71],"preservation,":[72,74],"meaning":[73],"divergence,":[76],"as":[77],"proxy":[79],"privacy.":[81],"metrics":[84],"corresponding":[85],"each":[87],"aspect.":[88],"Moreover,":[89],"through":[90],"strategies":[95],"representative":[97],"tasks":[98],"baselines":[100],"across":[101],"domains,":[102],"demonstrate":[104],"relation":[106,137],"between":[107],"quality":[109],"user":[113],"generated":[114],"content,":[115],"strategies,":[117],"metrics,":[118],"downstream":[120],"performance.":[121],"To":[122],"our":[123,125],"knowledge,":[124],"work":[126],"first":[129],"unified":[130],"text":[135],"specified":[140],"aspects,":[141],"offering":[142],"both":[143],"intrinsic":[144],"extrinsic":[146],"evaluation.":[147],"envisage":[149],"it":[150],"will":[151],"developments":[153],"towards":[154],"shareable,":[155],"high-quality":[156],"data.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}