{"id":"https://openalex.org/W7126393485","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.144","title":"Fine-tuning CLIP Text Encoders with Two-step Paraphrasing","display_name":"Fine-tuning CLIP Text Encoders with Two-step Paraphrasing","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126393485","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.144"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.144","pdf_url":"https://aclanthology.org/2024.findings-eacl.144.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.144.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083644268","display_name":"Hyunjae Kim","orcid":"https://orcid.org/0000-0003-2996-2564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunjae Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Seunghyun Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunghyun Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124621290","display_name":"Trung Bui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trung Bui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024521336","display_name":"Handong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Handong Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460493","display_name":"Qu\u00e2n Tran","orcid":"https://orcid.org/0000-0002-5769-3480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028863551","display_name":"Franck Dernoncourt","orcid":"https://orcid.org/0000-0002-1119-1346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franck Dernoncourt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124614959","display_name":"Jaewoo Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaewoo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7025109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2175","last_page":"2184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.44029998779296875,"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/T11269","display_name":"Algorithms and Data Compression","score":0.44029998779296875,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.21699999272823334,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.03849999979138374,"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/encoder","display_name":"Encoder","score":0.43849998712539673},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.271699994802475},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2678000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285999774932861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24699999392032623},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24480000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.144","pdf_url":"https://aclanthology.org/2024.findings-eacl.144.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.144","pdf_url":"https://aclanthology.org/2024.findings-eacl.144.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2906057384","display_name":null,"funder_award_id":"IITP-2024-2020-0-01819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3497368782","display_name":null,"funder_award_id":"NRF-2023R1A2C3004176","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7071920538","display_name":null,"funder_award_id":"IITP-2024-2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8018065544","display_name":null,"funder_award_id":"2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8932255049","display_name":null,"funder_award_id":"2023R1A2C3004176","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126393485.pdf","grobid_xml":"https://content.openalex.org/works/W7126393485.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"language-image":[1],"pre-training":[2],"(CLIP)":[3],"models":[4,35,78,132],"have":[5],"demonstrated":[6],"considerable":[7],"success":[8],"across":[9,133],"various":[10,134],"vision-language":[11],"tasks,":[12,135],"such":[13,47],"as":[14,48,155,157],"text-to-image":[15],"retrieval,":[16],"where":[17,88],"the":[18,74,107,117],"model":[19],"is":[20],"required":[21],"to":[22,28,53,72,146],"effectively":[23],"process":[24],"natural":[25],"language":[26,103],"input":[27,45],"produce":[29],"an":[30],"accurate":[31],"visual":[32],"output.However,":[33],"current":[34],"still":[36],"face":[37],"limitations":[38],"in":[39,44,61],"dealing":[40],"with":[41],"linguistic":[42],"variations":[43],"queries,":[46],"paraphrases,":[49],"making":[50],"it":[51],"challenging":[52],"handle":[54],"a":[55,68,83],"broad":[56],"range":[57],"of":[58,76,94],"user":[59],"queries":[60],"real-world":[62],"applications.In":[63],"this":[64],"study,":[65],"we":[66,89,105,123],"introduce":[67],"straightforward":[69],"fine-tuning":[70],"approach":[71,81],"enhance":[73],"representations":[75],"CLIP":[77,108,131],"for":[79],"paraphrases.Our":[80],"involves":[82],"two-step":[84],"paraphrase":[85],"generation":[86],"process,":[87],"automatically":[90],"create":[91],"two":[92],"categories":[93],"paraphrases":[95,114],"from":[96],"web-scale":[97],"image":[98,118],"captions":[99],"by":[100,144],"leveraging":[101],"large":[102],"models.Subsequently,":[104],"fine-tune":[106],"text":[109],"encoder":[110],"using":[111],"these":[112],"generated":[113],"while":[115],"freezing":[116],"encoder.Our":[119],"resulting":[120],"model,":[121],"which":[122],"call":[124],"ParaCLIP,":[125],"exhibits":[126],"significant":[127],"improvements":[128],"over":[129],"baseline":[130],"including":[136],"paraphrased":[137],"retrieval":[138],"(with":[139],"rank":[140],"similarity":[141,161],"scores":[142],"improved":[143],"up":[145],"2.0%":[147],"and":[148,153],"5.6%),":[149],"Visual":[150],"Genome":[151],"Relation":[152],"Attribution,":[154],"well":[156],"seven":[158],"semantic":[159],"textual":[160],"tasks.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}