{"id":"https://openalex.org/W4396832230","doi":"https://doi.org/10.1145/3613904.3642943","title":"Natural Language Dataset Generation Framework for Visualizations Powered by Large Language Models","display_name":"Natural Language Dataset Generation Framework for Visualizations Powered by Large Language Models","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396832230","doi":"https://doi.org/10.1145/3613904.3642943"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642943","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642943","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642943","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642943","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088950204","display_name":"Hyung-Kwon Ko","orcid":"https://orcid.org/0000-0002-6488-607X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Kwon Ko","raw_affiliation_strings":["School of Computing, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-6488-607X","affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506748","display_name":"Hyeon Jeon","orcid":"https://orcid.org/0000-0002-9659-2922"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeon Jeon","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-9659-2922","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Korea, Republic of","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038636760","display_name":"Gwanmo Park","orcid":"https://orcid.org/0000-0003-2320-2070"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gwanmo Park","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0003-2320-2070","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Korea, Republic of","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374581","display_name":"Dae Hyun Kim","orcid":"https://orcid.org/0000-0002-8657-9986"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dae Hyun Kim","raw_affiliation_strings":["Information & Electronics Research Institute, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-8657-9986","affiliations":[{"raw_affiliation_string":"Information & Electronics Research Institute, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004813317","display_name":"Nam Wook Kim","orcid":"https://orcid.org/0000-0003-4899-6671"},"institutions":[{"id":"https://openalex.org/I103531236","display_name":"Boston College","ror":"https://ror.org/02n2fzt79","country_code":"US","type":"education","lineage":["https://openalex.org/I103531236"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Wook Kim","raw_affiliation_strings":["Computer Science, Boston College, United States"],"raw_orcid":"https://orcid.org/0000-0003-4899-6671","affiliations":[{"raw_affiliation_string":"Computer Science, Boston College, United States","institution_ids":["https://openalex.org/I103531236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079709359","display_name":"Juho Kim","orcid":"https://orcid.org/0000-0001-6348-4127"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juho Kim","raw_affiliation_strings":["School of Computing, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0001-6348-4127","affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012388103","display_name":"Jinwook Seo","orcid":"https://orcid.org/0000-0002-7734-822X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinwook Seo","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-7734-822X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Korea, Republic of","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7184,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94309656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9932000041007996,"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":0.8447644114494324},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7885241508483887},{"id":"https://openalex.org/keywords/chart","display_name":"Chart","score":0.7093554735183716},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6068755388259888},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5985810160636902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5316622257232666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309759378433228},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5203304290771484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4554268419742584},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32797741889953613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447644114494324},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7885241508483887},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.7093554735183716},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6068755388259888},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5985810160636902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5316622257232666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309759378433228},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5203304290771484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4554268419742584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32797741889953613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613904.3642943","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642943","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642943","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642943","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642943","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642943","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396832230.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W1540555466","https://openalex.org/W1896226795","https://openalex.org/W1961845056","https://openalex.org/W2083928261","https://openalex.org/W2113411758","https://openalex.org/W2127008633","https://openalex.org/W2132881639","https://openalex.org/W2152922709","https://openalex.org/W2160382748","https://openalex.org/W2274505579","https://openalex.org/W2295423240","https://openalex.org/W2428096022","https://openalex.org/W2516678343","https://openalex.org/W2534380090","https://openalex.org/W2537060787","https://openalex.org/W2595457065","https://openalex.org/W2601243251","https://openalex.org/W2601982504","https://openalex.org/W2610226709","https://openalex.org/W2752843814","https://openalex.org/W2753472863","https://openalex.org/W2765874585","https://openalex.org/W2769533150","https://openalex.org/W2795226127","https://openalex.org/W2798413829","https://openalex.org/W2805655759","https://openalex.org/W2888611489","https://openalex.org/W2888660171","https://openalex.org/W2897132999","https://openalex.org/W2965346190","https://openalex.org/W2970641574","https://openalex.org/W3014820286","https://openalex.org/W3021218348","https://openalex.org/W3028907449","https://openalex.org/W3080485811","https://openalex.org/W3081277912","https://openalex.org/W3090149233","https://openalex.org/W3092587559","https://openalex.org/W3093933617","https://openalex.org/W3121499663","https://openalex.org/W3124602076","https://openalex.org/W3128915501","https://openalex.org/W3134547365","https://openalex.org/W3153965221","https://openalex.org/W3163379691","https://openalex.org/W3164045210","https://openalex.org/W3172214016","https://openalex.org/W3174906424","https://openalex.org/W3198767185","https://openalex.org/W3213578841","https://openalex.org/W4221143046","https://openalex.org/W4221149883","https://openalex.org/W4230939871","https://openalex.org/W4237375617","https://openalex.org/W4249415694","https://openalex.org/W4286908050","https://openalex.org/W4293251875","https://openalex.org/W4297094736","https://openalex.org/W4298206967","https://openalex.org/W4302275696","https://openalex.org/W4302312091","https://openalex.org/W4307475337","https://openalex.org/W4309674289","https://openalex.org/W4366549000","https://openalex.org/W4366549916","https://openalex.org/W4379533921","https://openalex.org/W6945001032"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W4391150403","https://openalex.org/W2081749821","https://openalex.org/W1968572830","https://openalex.org/W2090814745","https://openalex.org/W2029896371","https://openalex.org/W2136497797"],"abstract_inverted_index":{"We":[0,84],"introduce":[1],"VL2NL,":[2],"a":[3,50,68,72,87],"Large":[4],"Language":[5,27],"Model":[6],"(LLM)":[7],"framework":[8,149],"that":[9,57,95],"generates":[10],"rich":[11],"and":[12,39,99,115,121,129,132,148,158],"diverse":[13],"NL":[14,45,65,77,146],"datasets":[15,66,147],"using":[16],"Vega-Lite":[17,93],"specifications":[18,94],"as":[19],"input,":[20],"thereby":[21],"streamlining":[22],"the":[23,139],"development":[24],"of":[25,90],"Natural":[26],"Interfaces":[28],"(NLIs)":[29],"for":[30],"data":[31],"visualization.":[32],"To":[33],"synthesize":[34],"relevant":[35],"chart":[36,103,109,113,159],"semantics":[37,114],"accurately":[38],"enhance":[40],"syntactic":[41],"diversity":[42,98,136],"in":[43,67,153],"each":[44],"dataset,":[46],"we":[47,142],"leverage":[48],"1)":[49],"guided":[51],"discovery":[52],"incorporated":[53],"into":[54],"prompting":[55],"so":[56],"LLMs":[58],"can":[59,150],"steer":[60],"themselves":[61],"to":[62,75,138],"create":[63],"faithful":[64],"self-directed":[69],"manner;":[70],"2)":[71],"score-based":[73],"paraphrasing":[74,130],"augment":[76],"syntax":[78],"along":[79],"with":[80,119,134],"four":[81],"language":[82],"axes.":[83],"also":[85,126],"present":[86],"new":[88],"collection":[89,160],"1,981":[91],"real-world":[92,154],"have":[96],"increased":[97],"complexity":[100],"than":[101],"existing":[102],"collections.":[104],"When":[105],"tested":[106],"on":[107],"our":[108,145],"collection,":[110],"VL2NL":[111],"extracted":[112],"generated":[116],"L1/L2":[117],"captions":[118],"89.4%":[120],"76.0%":[122],"accuracy,":[123],"respectively.":[124],"It":[125],"demonstrated":[127],"generating":[128],"utterances":[131],"questions":[133],"greater":[135],"compared":[137],"benchmarks.":[140],"Last,":[141],"discuss":[143],"how":[144],"be":[151],"utilized":[152],"scenarios.":[155],"The":[156],"codes":[157],"are":[161],"available":[162],"at":[163],"https://github.com/hyungkwonko/chart-llm.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-05-12T00:00:00"}