{"id":"https://openalex.org/W4389518247","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur\u2019anic IR in English and Arabic","display_name":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur\u2019anic IR in English and Arabic","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518247","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.7","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.7.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.arabicnlp-1.7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074878714","display_name":"Vera Pavlova","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vera Pavlova","raw_affiliation_strings":["Dubai, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dubai, UAE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5074878714"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5137,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65386652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.002899999963119626,"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/T10627","display_name":"Advanced Image and Video Retrieval 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"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.8339999914169312},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9929999709129333},{"id":"https://openalex.org/keywords/arabic-language-models","display_name":"Arabic language models","score":0.6320000290870667},{"id":"https://openalex.org/keywords/english-language-models","display_name":"English language models","score":0.7350000143051147},{"id":"https://openalex.org/keywords/cross-lingual-transfer","display_name":"cross-lingual transfer","score":0.734000027179718},{"id":"https://openalex.org/keywords/multilingual-information-retrieval","display_name":"multilingual information retrieval","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306893706321716},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7419527173042297},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6940708756446838},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6483815908432007},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.636982262134552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164554119110107},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4753532111644745},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4515858292579651},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44206932187080383},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.41843071579933167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18203073740005493},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.11261898279190063},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.arabicnlp-1.7","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.7.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.02803","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02803","pdf_url":"https://arxiv.org/pdf/2312.02803","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.02803","doi":"https://doi.org/10.48550/arxiv.2312.02803","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.02803","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.7","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.7","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.7.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322472","display_name":"Qatar University","ror":"https://ror.org/00yhnba62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518247.pdf","grobid_xml":"https://content.openalex.org/works/W4389518247.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W1840435438","https://openalex.org/W2127589108","https://openalex.org/W2131676173","https://openalex.org/W2296073425","https://openalex.org/W2607892599","https://openalex.org/W2611029872","https://openalex.org/W2626778328","https://openalex.org/W2798482016","https://openalex.org/W2798858969","https://openalex.org/W2891555348","https://openalex.org/W2937975340","https://openalex.org/W2951534261","https://openalex.org/W2952370363","https://openalex.org/W2962369866","https://openalex.org/W2963341956","https://openalex.org/W2969574947","https://openalex.org/W2970641574","https://openalex.org/W2971296908","https://openalex.org/W2983040767","https://openalex.org/W2999262142","https://openalex.org/W3008110149","https://openalex.org/W3015883388","https://openalex.org/W3017604292","https://openalex.org/W3017961061","https://openalex.org/W3034439313","https://openalex.org/W3035102548","https://openalex.org/W3045210825","https://openalex.org/W3046375318","https://openalex.org/W3088148579","https://openalex.org/W3093334098","https://openalex.org/W3093517588","https://openalex.org/W3123742938","https://openalex.org/W3134155512","https://openalex.org/W3156836409","https://openalex.org/W3168875417","https://openalex.org/W3169483174","https://openalex.org/W3182591145","https://openalex.org/W3195577433","https://openalex.org/W3198713493","https://openalex.org/W3204880395","https://openalex.org/W3206455169","https://openalex.org/W3217305727","https://openalex.org/W4200635123","https://openalex.org/W4221152448","https://openalex.org/W4246183800","https://openalex.org/W4287207977","https://openalex.org/W4288076474","https://openalex.org/W4295065948","https://openalex.org/W4297808394","https://openalex.org/W4308613717","https://openalex.org/W4311183537","https://openalex.org/W4380687254","https://openalex.org/W4385565028","https://openalex.org/W4385573147","https://openalex.org/W4386566638"],"related_works":["https://openalex.org/W4416037457","https://openalex.org/W4416037779","https://openalex.org/W3212971727","https://openalex.org/W7020664373","https://openalex.org/W4411628394","https://openalex.org/W4406604208","https://openalex.org/W4280605992","https://openalex.org/W4404782965","https://openalex.org/W7153885563","https://openalex.org/W4416037786"],"abstract_inverted_index":{"In":[0],"this":[1,29,116],"work,":[2],"we":[3,23,48,73,179],"approach":[4],"the":[5,16,68,89,125,139,142,147,151,168,190,199,213],"problem":[6],"of":[7,38,56,70,100,118,124,141,192],"Qur'anic":[8,92,169,202],"information":[9],"retrieval":[10,33,143,184,200],"(IR)":[11],"in":[12,20,83,91,110,159,186],"Arabic":[13,160,187,208],"and":[14,60,85,97,104,120,129,207,215,221],"English.Using":[15],"latest":[17],"state-of-the-art":[18,90],"methods":[19],"neural":[21],"IR,":[22],"research":[24],"what":[25],"helps":[26],"to":[27,43,114,137,161,177,188,197,211],"tackle":[28],"task":[30,109,185,204],"more":[31],"efficiently.Training":[32],"models":[34,144,157,220],"requires":[35],"a":[36,53,75],"lot":[37],"data,":[39,72],"which":[40,79,135],"is":[41],"difficult":[42],"obtain":[44],"for":[45,94,107],"training":[46,51,63],"in-domain.Therefore,":[47],"commence":[49],"with":[50,167,183],"on":[52,64],"large":[54],"amount":[55],"general":[57,193],"domain":[58,194],"data":[59,76],"then":[61],"continue":[62],"in-domain":[65,71],"data.To":[66],"handle":[67],"lack":[69,117],"employed":[74],"augmentation":[77],"technique,":[78],"considerably":[80],"improved":[81],"results":[82],"MRR@10":[84],"NDCG@5":[86],"metrics,":[87],"setting":[88],"IR":[93,108,170,203],"both":[95],"English":[96,111,176,206],"Arabic.The":[98],"absence":[99],"an":[101],"Islamic":[102,126],"corpus":[103,127],"domainspecific":[105],"model":[106,132],"motivated":[112],"us":[113,210],"address":[115],"resources":[119],"take":[121],"preliminary":[122],"steps":[123],"compilation":[128],"domain-specific":[130,148],"language":[131,156],"(LM)":[133],"pre-training,":[134],"helped":[136],"improve":[138],"performance":[140],"that":[145,164],"use":[146],"LM":[149],"as":[150],"shared":[152],"backbone.We":[153],"examined":[154],"several":[155],"(LMs)":[158],"select":[162],"one":[163],"efficiently":[165],"deals":[166],"task.Besides":[171],"transferring":[172],"successful":[173],"experiments":[174,182],"from":[175],"Arabic,":[178],"conducted":[180],"additional":[181],"amortize":[189],"scarcity":[191],"datasets":[195],"used":[196],"train":[198],"models.Handling":[201],"combining":[205],"allowed":[209],"enhance":[212],"comparison":[214],"share":[216],"valuable":[217],"insights":[218],"across":[219],"languages.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-12-10T00:00:00"}