{"id":"https://openalex.org/W7130530810","doi":"https://doi.org/10.1109/ictc66702.2025.11388076","title":"Prompt Disambiguation for Text-to-Image Generation","display_name":"Prompt Disambiguation for Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130530810","doi":"https://doi.org/10.1109/ictc66702.2025.11388076"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126393108","display_name":"Woojin Na","orcid":null},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woojin Na","raw_affiliation_strings":["Ajou University,Dept. of Electrical and Computer Engineering,Suwon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajou University,Dept. of Electrical and Computer Engineering,Suwon,Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126417395","display_name":"Minjun Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjun Kang","raw_affiliation_strings":["Ajou University,Dept. of Artificial Intelligence,Suwon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajou University,Dept. of Artificial Intelligence,Suwon,Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122865999","display_name":"Hyung Il Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Il Koo","raw_affiliation_strings":["Ajou University,Dept. of Electrical and Computer Engineering,Suwon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajou University,Dept. of Electrical and Computer Engineering,Suwon,Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57664883"],"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":"161","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2800999879837036,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2800999879837036,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.19699999690055847,"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/T10799","display_name":"Data Visualization and Analytics","score":0.0681999996304512,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.7441999912261963},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6783999800682068},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5181999802589417},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5052000284194946},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5026999711990356},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.483599990606308},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.46480000019073486},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38749998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050000071525574},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.7441999912261963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6897000074386597},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6783999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3034675880","https://openalex.org/W3193147816","https://openalex.org/W3199400376","https://openalex.org/W4235505822","https://openalex.org/W4285250447","https://openalex.org/W4312933868","https://openalex.org/W4394948163","https://openalex.org/W4406174915"],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"diffusion":[2,133],"models,":[3],"such":[4],"as":[5],"Stable":[6],"Diffusion":[7],"and":[8,57,64,93,124,139,190],"DALL\u00b7E":[9],"2,":[10],"have":[11],"demonstrated":[12],"remarkable":[13],"generative":[14],"capabilities.":[15],"However,":[16,50],"they":[17],"often":[18],"struggle":[19],"with":[20,168],"lexically":[21],"ambiguous":[22,91],"prompts,":[23],"resulting":[24],"in":[25,81,158,193],"outputs":[26],"that":[27,178],"conflate":[28],"or":[29,43],"misinterpret":[30],"multiple":[31],"word":[32],"senses.":[33],"Prior":[34],"approaches":[35],"addressed":[36],"this":[37,70],"issue":[38],"through":[39],"prompt":[40,79,108],"design":[41],"guidelines":[42],"interactive":[44],"workflows":[45],"based":[46],"on":[47],"user":[48],"feedback.":[49],"these":[51],"methods":[52],"require":[53],"repeated":[54],"human":[55,160],"intervention":[56],"lack":[58],"the":[59,107,121,127,144,150,155,169,173],"ability":[60],"to":[61,142,183],"automatically":[62],"detect":[63],"resolve":[65],"lexical":[66,180],"ambiguity.":[67],"To":[68],"address":[69],"limitation,":[71],"we":[72,153],"propose":[73],"a":[74,99,110,114,131],"fully":[75],"automated":[76],"pipeline":[77,85],"for":[78],"disambiguation":[80],"T2I":[82,132,194],"generation.":[83],"The":[84],"comprises":[86],"three":[87],"stages:":[88],"(1)":[89],"detecting":[90],"words":[92],"selecting":[94],"appropriate":[95],"WordNet":[96],"glosses":[97],"via":[98],"Word":[100],"Sense":[101],"Disambiguation":[102],"(WSD)":[103],"model;":[104],"(2)":[105],"rewriting":[106],"into":[109],"disambiguated":[111],"version":[112],"using":[113,130],"large":[115],"language":[116],"model":[117],"(LLM)":[118],"informed":[119],"by":[120],"selected":[122],"glosses;":[123],"(3)":[125],"generating":[126],"final":[128],"image":[129,166,184],"model.":[134],"We":[135],"conduct":[136],"both":[137],"qualitative":[138],"quantitative":[140,151],"evaluations":[141],"assess":[143,162],"effectiveness":[145],"of":[146,172],"our":[147],"method.":[148],"For":[149],"evaluation,":[152],"use":[154],"V-LAB":[156],"benchmark,":[157],"which":[159],"annotators":[161],"whether":[163],"each":[164],"generated":[165],"aligns":[167],"intended":[170],"meaning":[171],"prompt.":[174],"Our":[175],"results":[176],"demonstrate":[177],"resolving":[179],"ambiguity":[181],"prior":[182],"generation":[185],"significantly":[186],"improves":[187],"semantic":[188],"fidelity":[189],"output":[191],"consistency":[192],"models.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}