{"id":"https://openalex.org/W7139935997","doi":"https://doi.org/10.1016/j.procs.2026.01.034","title":"Arabic Legal Information Retrieval: The Impact of Morphological Segmentation and Semantic Embeddings","display_name":"Arabic Legal Information Retrieval: The Impact of Morphological Segmentation and Semantic Embeddings","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139935997","doi":"https://doi.org/10.1016/j.procs.2026.01.034"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.034","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.034","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.034","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119723244","display_name":"Rawan AboAsal","orcid":null},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Rawan Aboasal","raw_affiliation_strings":["School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841","institution_ids":["https://openalex.org/I57629906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130248047","display_name":"Salma Montasser","orcid":null},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Salma Montasser","raw_affiliation_strings":["School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841","institution_ids":["https://openalex.org/I57629906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130222715","display_name":"Fouad Hossam Eldin","orcid":null},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Fouad Hossam Eldin","raw_affiliation_strings":["School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841","institution_ids":["https://openalex.org/I57629906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130236778","display_name":"Ali Abdelwahab","orcid":null},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Abdelwahab","raw_affiliation_strings":["School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841","institution_ids":["https://openalex.org/I57629906"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081801413","display_name":"Hazem Abdelazim","orcid":null},"institutions":[{"id":"https://openalex.org/I57629906","display_name":"Nile University","ror":"https://ror.org/03cg7cp61","country_code":"EG","type":"education","lineage":["https://openalex.org/I57629906"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Hazem Abdelazim","raw_affiliation_strings":["School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technologies ESLSCA University Giza, Egypt, 11841","institution_ids":["https://openalex.org/I57629906"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119723244"],"corresponding_institution_ids":["https://openalex.org/I57629906"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93283311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"275","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.37450000643730164,"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/T10028","display_name":"Topic Modeling","score":0.37450000643730164,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.12060000002384186,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06629999727010727,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.647599995136261},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.620199978351593},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.373199999332428},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.3555999994277954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32010000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9229999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632999777793884},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.647599995136261},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6190999746322632},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.3555999994277954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28769999742507935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.034","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.034","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.034","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.034","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1994842363","https://openalex.org/W2024244759","https://openalex.org/W2041349462","https://openalex.org/W2922098300","https://openalex.org/W2970641574","https://openalex.org/W3021397474","https://openalex.org/W3157758108","https://openalex.org/W4252076394","https://openalex.org/W4282976329","https://openalex.org/W4317951944","https://openalex.org/W4327594639","https://openalex.org/W4385567034","https://openalex.org/W4385573622","https://openalex.org/W4389276314","https://openalex.org/W4391843256","https://openalex.org/W4402670856","https://openalex.org/W4402671213","https://openalex.org/W4403770186","https://openalex.org/W7105704295"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"systems":[3],"are":[4],"now":[5],"considered":[6,44],"the":[7,16,31,37,50,58,63,80,114,126,132,174,191,232,240,249],"foundation":[8],"of":[9,36,62,82,98,116,166,234,242],"modern":[10],"Agentic":[11,269],"AI":[12],"solutions;":[13],"it":[14],"closes":[15],"gap":[17],"between":[18],"knowledge":[19],"retrieval":[20,38,41,71,142,238,267],"and":[21,33,54,57,86,102,111,157,160,200,207,260,268],"generative":[22],"reasoning.":[23],"However,":[24],"their":[25],"total":[26],"effectiveness":[27],"critically":[28],"depends":[29],"on":[30,79],"quality":[32],"linguistic":[34],"adaptability":[35],"layer.":[39],"Information":[40],"is":[42],"still":[43],"a":[45,92,210,254],"difficult":[46,59],"task":[47],"due":[48],"to":[49,107,112,129,181],"Arabic":[51,64,74,244,264],"language\u2019s":[52],"rich":[53],"deep":[55],"morphology":[56],"domain-specific":[60],"characteristics":[61],"legal":[65,75,100,119,245,265],"terminology.":[66],"This":[67],"study":[68],"explores":[69],"different":[70],"models":[72,143,184],"for":[73,135,257],"texts,":[76],"while":[77,248],"focusing":[78],"combination":[81],"morphological":[83,162,167],"analysis":[84,168],"(Farasa)":[85,215],"semantic":[87],"embedding":[88,149],"representations.":[89],"We":[90,121,138],"constructed":[91],"synthetic":[93,251],"benchmark":[94],"dataset":[95,252],"made":[96],"up":[97],"500":[99],"articles":[101],"1,000":[103],"question\u2013answer":[104],"pairs,":[105],"just":[106],"support":[108],"reproducible":[109,261],"evaluation":[110],"address":[113],"scarcity":[115],"publicly":[117],"available":[118],"datasets.":[120],"used":[122],"answers":[123],"generated":[124],"by":[125],"GPT-4.1-mini":[127],"API,":[128],"act":[130],"as":[131,145],"ground":[133],"truth":[134],"model":[136],"assessment.":[137],"evaluate":[139],"traditional":[140],"lexical":[141],"such":[144],"BM25":[146,214],"against":[147],"advanced":[148],"based":[150],"models,":[151],"including":[152],"Ada":[153,217],"v3,":[154],"BGE":[155],"M3,":[156],"GTE,":[158],"with":[159,188,216],"without":[161],"preprocessing.":[163],"The":[164],"inclusion":[165],"substantially":[169],"enhances":[170],"BM25\u2019s":[171],"performance,":[172],"increasing":[173],"Mean":[175],"Average":[176],"Precision":[177],"(MAP)":[178],"from":[179],"0.7178":[180],"0.7715.":[182],"Embedding-based":[183],"also":[185],"performed":[186],"well,":[187],"Mistral-embed":[189],"achieving":[190],"highest":[192],"overall":[193],"scores":[194],"among":[195],"them":[196],"(MAP":[197,223],"=":[198,202,224,227],"0.7570":[199],"nDCG@10":[201,226],"0.7964),":[203],"slightly":[204],"outperforming":[205],"GTE":[206],"BGE-M3.":[208],"Moreover,":[209],"hybrid":[211],"configuration":[212],"combining":[213],"v3":[218],"embeddings":[219],"yields":[220],"improved":[221],"results":[222],"0.8304;":[225],"0.8626).":[228],"These":[229],"findings":[230],"highlight":[231],"importance":[233],"morphology-aware,":[235],"semantically":[236],"grounded":[237],"in":[239,263],"construction":[241],"robust":[243],"RAG":[246],"pipelines,":[247],"introduced":[250],"provides":[253],"valuable":[255],"resource":[256],"future":[258],"benchmarking":[259],"research":[262],"information":[266],"AI.":[270]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}