{"id":"https://openalex.org/W4404783282","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.265","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","display_name":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404783282","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.265"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.265","pdf_url":"https://aclanthology.org/2024.emnlp-main.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.265.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiacong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiacong Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055505540","display_name":"Bohong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030353385","display_name":"Jiang Haiyong","orcid":"https://orcid.org/0000-0001-7279-3810"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyong Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198510","display_name":"Xun Zhou","orcid":"https://orcid.org/0000-0003-4930-6572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Xun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511035","display_name":"Xin Xiao","orcid":"https://orcid.org/0000-0002-9274-137X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596657","display_name":"Haoyuan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyuan Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076518693","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-1799-3948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3345,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68339445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4608","last_page":"4623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.9316999912261963,"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":0.7552597522735596},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7147622108459473},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.662907063961029},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5746188163757324},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3739890456199646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22941464185714722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552597522735596},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7147622108459473},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.662907063961029},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5746188163757324},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3739890456199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22941464185714722},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.265","pdf_url":"https://aclanthology.org/2024.emnlp-main.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.265","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.265","pdf_url":"https://aclanthology.org/2024.emnlp-main.265.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1033401312","display_name":null,"funder_award_id":"62206263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G164487479","display_name":null,"funder_award_id":"62102393","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G194855440","display_name":null,"funder_award_id":"62476262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2676125936","display_name":null,"funder_award_id":"2022T150639","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3832874031","display_name":null,"funder_award_id":"2022T150639","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5104556479","display_name":null,"funder_award_id":"62271467","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6871481020","display_name":null,"funder_award_id":"U21A20515","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7793919633","display_name":null,"funder_award_id":"6227146","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8565926968","display_name":null,"funder_award_id":"U21A2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G880636097","display_name":null,"funder_award_id":"62306296","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404783282.pdf","grobid_xml":"https://content.openalex.org/works/W4404783282.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,25,34],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"and":[6,36,42,84,109],"the":[7,63,74,86,97,120,132],"scarcity":[8],"of":[9,32,100,125],"high-quality":[10],"multimodal":[11],"alignment":[12],"data":[13,21,27,58],"have":[14,95],"inspired":[15],"numerous":[16],"researches":[17],"on":[18],"synthetic":[19],"VLM":[20,26,40,75],"generation.The":[22],"conventional":[23],"norm":[24],"construction":[28,59],"uses":[29],"a":[30,54,68,91],"mixture":[31],"specialists":[33],"caption":[35,136],"OCR,":[37],"or":[38],"stronger":[39],"APIs":[41],"expensive":[43],"human":[44],"annotation.In":[45],"this":[46],"paper,":[47],"we":[48],"present":[49],"World":[50],"to":[51,77],"Code":[52],"(W2C),":[53],"meticulously":[55],"curated":[56],"multi-modal":[57],"pipeline":[60,72],"that":[61,119],"organizes":[62],"final":[64],"generation":[65],"output":[66],"into":[67],"Python":[69],"code":[70,122],"format.The":[71],"leverages":[73],"itself":[76],"extract":[78],"cross-modal":[79],"information":[80],"via":[81,90],"different":[82,114],"prompts":[83],"filter":[85],"generated":[87],"outputs":[88],"again":[89],"consistency":[92],"filtering":[93],"strategy.Experiments":[94],"demonstrated":[96],"high":[98],"quality":[99],"W2C":[101],"by":[102],"improving":[103],"various":[104],"existing":[105],"visual":[106,110],"question":[107],"answering":[108],"grounding":[111],"benchmarks":[112],"across":[113],"VLMs.Further":[115],"analysis":[116],"also":[117],"demonstrates":[118],"new":[121],"parsing":[123],"ability":[124],"VLMs":[126],"presents":[127],"better":[128],"crossmodal":[129],"equivalence":[130],"than":[131],"commonly":[133],"used":[134],"detail":[135],"ability.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}