{"id":"https://openalex.org/W3008884016","doi":"https://doi.org/10.1587/transinf.2019edp7065","title":"Leveraging Neural Caption Translation with Visually Grounded Paraphrase Augmentation","display_name":"Leveraging Neural Caption Translation with Visually Grounded Paraphrase Augmentation","publication_year":2020,"publication_date":"2020-02-29","ids":{"openalex":"https://openalex.org/W3008884016","doi":"https://doi.org/10.1587/transinf.2019edp7065","mag":"3008884016"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7065","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7065","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7065/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7065/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091846449","display_name":"Johanes Effendi","orcid":"https://orcid.org/0000-0001-5755-415X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Johanes EFFENDI","raw_affiliation_strings":["Augmented Human Communication Lab., Nara Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab., Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani SAKTI","raw_affiliation_strings":["Augmented Human Communication Lab., Nara Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab., Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhito SUDOH","raw_affiliation_strings":["Augmented Human Communication Lab., Nara Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab., Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi NAKAMURA","raw_affiliation_strings":["Augmented Human Communication Lab., Nara Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab., Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091846449"],"corresponding_institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.1359,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52853262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E103.D","issue":"3","first_page":"674","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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":0.9941999912261963,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9876000285148621,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.9693439602851868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8730341792106628},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.739005446434021},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7052294015884399},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6681686639785767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6678787469863892},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6117116212844849},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5900598764419556},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.5373119115829468},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5149713158607483},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4503057897090912},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0808706283569336}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9693439602851868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8730341792106628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.739005446434021},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7052294015884399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6681686639785767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6678787469863892},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6117116212844849},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5900598764419556},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.5373119115829468},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5149713158607483},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4503057897090912},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0808706283569336},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7065","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7065","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7065/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7065","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7065","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7065/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1688345242","display_name":null,"funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8777250574","display_name":"Research for unsupervised acoustic pattern discovery with zero resources","funder_award_id":"17K00237","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G947068629","display_name":null,"funder_award_id":"JP17K00237","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008884016.pdf","grobid_xml":"https://content.openalex.org/works/W3008884016.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1810943226","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1996430422","https://openalex.org/W2016172157","https://openalex.org/W2088892085","https://openalex.org/W2101105183","https://openalex.org/W2117405790","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2144600658","https://openalex.org/W2148708890","https://openalex.org/W2531908596","https://openalex.org/W2575629043","https://openalex.org/W2593341061","https://openalex.org/W2735824434","https://openalex.org/W2757877530","https://openalex.org/W2760101375","https://openalex.org/W2760425631","https://openalex.org/W2808470846","https://openalex.org/W2896457183","https://openalex.org/W2963331233","https://openalex.org/W2963909453","https://openalex.org/W2964003477","https://openalex.org/W2964138343"],"related_works":["https://openalex.org/W191017350","https://openalex.org/W3137243147","https://openalex.org/W4206666510","https://openalex.org/W2018298289","https://openalex.org/W2782520308","https://openalex.org/W3032998312","https://openalex.org/W1503094549","https://openalex.org/W3175194702","https://openalex.org/W4321512656","https://openalex.org/W2117607680"],"abstract_inverted_index":{"Since":[0],"a":[1,14,18,23,32,86,95,139,155,170],"concept":[2,99],"can":[3,118],"be":[4,120],"represented":[5],"by":[6,137],"different":[7],"vocabularies,":[8],"styles,":[9],"and":[10,77,145],"levels":[11],"of":[12,25,34,97],"detail,":[13],"translation":[15,51],"task":[16,21],"resembles":[17],"many-to-many":[19],"mapping":[20],"from":[22],"distribution":[24,33,64],"sentences":[26,35],"in":[27,36,47,100,154],"the":[28,37,63,73,98,105,110,130],"source":[29],"language":[30],"into":[31,126],"target":[38],"language.":[39],"This":[40],"viewpoint,":[41],"however,":[42],"is":[43,54],"not":[44],"fully":[45],"implemented":[46],"current":[48],"neural":[49,147],"machine":[50],"(NMT),":[52],"which":[53,70,91],"one-to-one":[55],"sentence":[56],"mapping.":[57],"In":[58,113],"this":[59,114,135],"study,":[60],"we":[61],"represent":[62],"itself":[65],"as":[66,94,122,151],"multiple":[67],"paraphrase":[68,89],"sentences,":[69],"will":[71],"enrich":[72],"model":[74],"context":[75],"understanding":[76],"trigger":[78],"it":[79],"to":[80,102],"produce":[81],"numerous":[82],"hypotheses.":[83],"We":[84,133],"use":[85],"visually":[87],"grounded":[88],"(VGP),":[90],"uses":[92],"images":[93],"constraint":[96],"paraphrasing,":[101],"guarantee":[103],"that":[104,142,149,161],"created":[106],"paraphrases":[107],"are":[108],"within":[109],"intended":[111],"distribution.":[112],"way,":[115],"our":[116,162],"method":[117],"also":[119],"considered":[121],"incorporating":[123],"image":[124,131],"information":[125],"NMT":[127,172],"without":[128],"using":[129],"itself.":[132],"implement":[134],"idea":[136],"crowdsourcing":[138],"paraphrasing":[140,148],"corpus":[141],"realizes":[143],"VGP":[144,164],"construct":[146],"behaves":[150],"expert":[152],"models":[153],"NMT.":[156],"Our":[157],"experimental":[158],"results":[159],"reveal":[160],"proposed":[163],"augmentation":[165],"strategies":[166],"showed":[167],"improvement":[168],"against":[169],"vanilla":[171],"baseline.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
