{"id":"https://openalex.org/W4389009503","doi":"https://doi.org/10.18653/v1/2022.inlg-main.4","title":"Arabic Image Captioning using Pre-training of Deep Bidirectional Transformers","display_name":"Arabic Image Captioning using Pre-training of Deep Bidirectional Transformers","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4389009503","doi":"https://doi.org/10.18653/v1/2022.inlg-main.4"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.inlg-main.4","doi":"https://doi.org/10.18653/v1/2022.inlg-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.inlg-main.4","pdf_url":"https://aclanthology.org/2022.inlg-main.4.pdf","source":{"id":"https://openalex.org/S4306419715","display_name":"International Conference on Natural Language Generation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 15th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.inlg-main.4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113054558","display_name":"Jonathan Emami","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonathan Emami","raw_affiliation_strings":["Lund University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069585870","display_name":"Pierre Nugues","orcid":"https://orcid.org/0000-0002-9563-4000","observed_orcids":["https://orcid.org/0000-0002-9563-4000"]},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Pierre Nugues","raw_affiliation_strings":["Lund University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069884464","display_name":"Ashraf Elnagar","orcid":"https://orcid.org/0000-0003-2265-7268","observed_orcids":["https://orcid.org/0000-0003-2265-7268"]},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ashraf Elnagar","raw_affiliation_strings":["University of Sharjah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sharjah","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000538231","display_name":"Imad Afyouni","orcid":"https://orcid.org/0000-0001-6686-3069","observed_orcids":["https://orcid.org/0000-0001-6686-3069"]},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Imad Afyouni","raw_affiliation_strings":["University of Sharjah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sharjah","institution_ids":["https://openalex.org/I29891158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7228,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90699918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":9.999999747378752e-05,"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":0.0,"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/bidirectional-transformer","display_name":"bidirectional transformer","score":0.7689999938011169},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5789999961853027},{"id":"https://openalex.org/keywords/oscar","display_name":"OSCAR","score":0.9179999828338623},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.8650000095367432},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/arabic-corpus","display_name":"Arabic corpus","score":0.6669999957084656},{"id":"https://openalex.org/keywords/human-evaluation","display_name":"human evaluation","score":0.4129999876022339}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9896257519721985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048869967460632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646241307258606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5876246690750122},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5700801014900208},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5672189593315125},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4931153953075409},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4780733585357666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4267309904098511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4133869707584381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3596474230289459},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11098942160606384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06305921077728271},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2022.inlg-main.4","doi":"https://doi.org/10.18653/v1/2022.inlg-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.inlg-main.4","pdf_url":"https://aclanthology.org/2022.inlg-main.4.pdf","source":{"id":"https://openalex.org/S4306419715","display_name":"International Conference on Natural Language Generation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 15th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:lup-student-papers.lub.lu.se:9077401","doi":null,"is_oa":false,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9077401","pdf_url":null,"source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"H2"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.inlg-main.4","doi":"https://doi.org/10.18653/v1/2022.inlg-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.inlg-main.4","pdf_url":"https://aclanthology.org/2022.inlg-main.4.pdf","source":{"id":"https://openalex.org/S4306419715","display_name":"International Conference on Natural Language Generation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 15th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6462591990","display_name":null,"funder_award_id":"04533","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G7939416468","display_name":"Semantica: Algorithms and Tools for Multilingual Knowledge Extraction","funder_award_id":"2021-04533","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389009503.pdf","grobid_xml":"https://content.openalex.org/works/W4389009503.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2604380351","https://openalex.org/W2626778328","https://openalex.org/W2805430858","https://openalex.org/W2809904748","https://openalex.org/W2963341956","https://openalex.org/W2986670728","https://openalex.org/W2997591391","https://openalex.org/W3008110149","https://openalex.org/W3011608779","https://openalex.org/W3038033387","https://openalex.org/W3045210825","https://openalex.org/W3084524316","https://openalex.org/W3091588028","https://openalex.org/W3106433641","https://openalex.org/W3113708896","https://openalex.org/W3173220247","https://openalex.org/W3196915641","https://openalex.org/W4226257165","https://openalex.org/W4312922092"],"related_works":["https://openalex.org/W4386753702","https://openalex.org/W4381094892","https://openalex.org/W4410718815","https://openalex.org/W4289866023","https://openalex.org/W7125797546","https://openalex.org/W4413173669","https://openalex.org/W4412462997","https://openalex.org/W4416037775","https://openalex.org/W3196915641","https://openalex.org/W4416037802"],"abstract_inverted_index":{"Image":[0],"captioning":[1,36,47,60,69,116,166],"is":[2,48,175],"the":[3,106,114],"process":[4],"of":[5,11,18,41,108,139,158],"automatically":[6],"generating":[7],"a":[8,15,39,66,89,156,176,181],"textual":[9],"description":[10],"an":[12,133],"image.It":[13],"has":[14,37],"wide":[16],"range":[17],"applications,":[19],"such":[20],"as":[21,100],"effective":[22],"image":[23,35,46,59,68,115,165],"search,":[24],"auto":[25],"archiving":[26],"and":[27,55,126,143,171],"even":[28],"helping":[29],"visually":[30],"impaired":[31],"people":[32],"to":[33,103,113],"see.English":[34],"seen":[38],"lot":[40],"development":[42],"lately,":[43],"while":[44],"Arabic":[45,58,79,169,183,186],"lagging":[49],"behind.In":[50],"this":[51],"work,":[52],"we":[53,82,148],"developed":[54],"evaluated":[56],"several":[57],"models":[61,73,167],"with":[62,74,85,128,152,168,185],"well-established":[63],"metrics":[64],"on":[65,77,155],"public":[67],"benchmark.We":[70],"initialized":[71],"all":[72],"transformers":[75],"pre-trained":[76],"different":[78],"corpora.After":[80],"initialization,":[81],"fine-tuned":[83],"them":[84],"image-caption":[86],"pairs":[87],"using":[88],"learning":[90,107],"method":[91],"called":[92],"OSCAR.OSCAR":[93],"uses":[94],"object":[95,173,187],"tags":[96,174],"detected":[97],"in":[98],"images":[99],"anchor":[101],"points":[102],"significantly":[104],"ease":[105],"image-text":[109],"semantic":[110],"alignments.In":[111],"relation":[112],"benchmark,":[117],"our":[118,150,159],"best":[119],"performing":[120],"model":[121],"scored":[122],"0.39,":[123],"0.25,":[124],"0.15":[125],"0.092":[127],"BLEU-1,2,3,4":[129],"respectively":[130],"1":[131],",":[132],"improvement":[134],"over":[135],"previously":[136],"published":[137],"scores":[138,151],"0.33,":[140],"0.19,":[141],"0.11":[142],"0.057.Beside":[144],"additional":[145],"evaluation":[146,154],"metrics,":[147],"complemented":[149],"human":[153],"sample":[157],"output.Our":[160],"experiments":[161],"showed":[162],"that":[163,180],"training":[164],"captions":[170],"English":[172],"working":[177],"approach,":[178],"but":[179],"pure":[182],"dataset,":[184],"tags,":[188],"would":[189],"be":[190],"preferable.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-11-27T00:00:00"}