{"id":"https://openalex.org/W4417023651","doi":"https://doi.org/10.54963/jic.v4i2.1706","title":"BERT and Beyond: A Comprehensive Survey of Natural Language Processing Techniques for Information Retrieval","display_name":"BERT and Beyond: A Comprehensive Survey of Natural Language Processing Techniques for Information Retrieval","publication_year":2025,"publication_date":"2025-09-06","ids":{"openalex":"https://openalex.org/W4417023651","doi":"https://doi.org/10.54963/jic.v4i2.1706"},"language":"en","primary_location":{"id":"doi:10.54963/jic.v4i2.1706","doi":"https://doi.org/10.54963/jic.v4i2.1706","is_oa":true,"landing_page_url":"https://doi.org/10.54963/jic.v4i2.1706","pdf_url":"https://ojs.ukscip.com/submissions_files/2/journals/4/articles/1706/69327702bcd35.pdf","source":{"id":"https://openalex.org/S4220651571","display_name":"Journal of Intelligent Communication","issn_l":"2754-5792","issn":["2754-5792"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Communication","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.ukscip.com/submissions_files/2/journals/4/articles/1706/69327702bcd35.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094024711","display_name":"Mokhtar Hussein Al-Sarori","orcid":"https://orcid.org/0000-0003-3620-0787","observed_orcids":["https://orcid.org/0000-0003-3620-0787"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mokhtar H. Al\u2011Sarori","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3620-0787","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080947386","display_name":"Mubarak Mohammed Al\u2010Ezzi Sufyan","orcid":"https://orcid.org/0000-0002-0443-6819","observed_orcids":["https://orcid.org/0000-0002-0443-6819"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mubarak Mohammed Al\u2011Ezzi Sufyan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0443-6819","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077815100","display_name":"Mahfoudh Saeed Al-Asaly","orcid":"https://orcid.org/0000-0002-4558-5394","observed_orcids":["https://orcid.org/0000-0002-4558-5394"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahfoudh Al\u2011Asaly","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4558-5394","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120228041","display_name":"Ghassan Abdullah Abdulwasea Al\u2010Maamari","orcid":"https://orcid.org/0009-0003-3623-9566","observed_orcids":["https://orcid.org/0009-0003-3623-9566"]},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]},{"id":"https://openalex.org/I4405254300","display_name":"University of Saba Region","ror":"https://ror.org/01nd4jr17","country_code":"YE","type":"education","lineage":["https://openalex.org/I4405254300"]}],"countries":["SA","YE"],"is_corresponding":false,"raw_author_name":"Ghassan Abdullah Abdulwasea Al\u2011Maamari","raw_affiliation_strings":["Department of Computer Information Systems, Al\u2011Jawf Faculty, University of Saba Region, Marib, Yemen","Department of Information Technology, College of Computer, Qassim University, Buraydah 51174, Saudi Arabia","Faculty of Information Technology & Computer Science, University of Saba Region, Marib, Yemen"],"raw_orcid":"https://orcid.org/0009-0003-3623-9566","affiliations":[{"raw_affiliation_string":"Department of Computer Information Systems, Al\u2011Jawf Faculty, University of Saba Region, Marib, Yemen","institution_ids":["https://openalex.org/I4405254300"]},{"raw_affiliation_string":"Department of Information Technology, College of Computer, Qassim University, Buraydah 51174, Saudi Arabia","institution_ids":["https://openalex.org/I156216236"]},{"raw_affiliation_string":"Faculty of Information Technology & Computer Science, University of Saba Region, Marib, Yemen","institution_ids":["https://openalex.org/I4405254300"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7586,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84973225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"4","issue":"2","first_page":"93","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9307000041007996,"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":0.9307000041007996,"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":0.06849999725818634,"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/T10203","display_name":"Recommender Systems and Techniques","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.9020000100135803},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.8920000195503235},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9620000123977661},{"id":"https://openalex.org/keywords/generative-retrieval","display_name":"generative retrieval","score":0.7799999713897705},{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.5389999747276306},{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.781000018119812},{"id":"https://openalex.org/keywords/cross-modal-retrieval","display_name":"cross-modal retrieval","score":0.9860000014305115},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.6420000195503235},{"id":"https://openalex.org/keywords/retrieval-ranking","display_name":"retrieval ranking","score":0.42399999499320984},{"id":"https://openalex.org/keywords/contextualized-embeddings","display_name":"contextual embeddings","score":0.6389999985694885},{"id":"https://openalex.org/keywords/evaluation-benchmark","display_name":"evaluation benchmark","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828999757766724},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45989999175071716},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.2867000102996826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.54963/jic.v4i2.1706","doi":"https://doi.org/10.54963/jic.v4i2.1706","is_oa":true,"landing_page_url":"https://doi.org/10.54963/jic.v4i2.1706","pdf_url":"https://ojs.ukscip.com/submissions_files/2/journals/4/articles/1706/69327702bcd35.pdf","source":{"id":"https://openalex.org/S4220651571","display_name":"Journal of Intelligent Communication","issn_l":"2754-5792","issn":["2754-5792"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Communication","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.54963/jic.v4i2.1706","doi":"https://doi.org/10.54963/jic.v4i2.1706","is_oa":true,"landing_page_url":"https://doi.org/10.54963/jic.v4i2.1706","pdf_url":"https://ojs.ukscip.com/submissions_files/2/journals/4/articles/1706/69327702bcd35.pdf","source":{"id":"https://openalex.org/S4220651571","display_name":"Journal of Intelligent Communication","issn_l":"2754-5792","issn":["2754-5792"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Communication","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417023651.pdf","grobid_xml":"https://content.openalex.org/works/W4417023651.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W3035745734","https://openalex.org/W4387355694","https://openalex.org/W4396600777","https://openalex.org/W4399400922","https://openalex.org/W4402854593","https://openalex.org/W4403796472","https://openalex.org/W4406840433","https://openalex.org/W4407820180","https://openalex.org/W4415152171","https://openalex.org/W6910671391","https://openalex.org/W6910741274","https://openalex.org/W6966545553","https://openalex.org/W7080713867","https://openalex.org/W7129489580","https://openalex.org/W7134117706"],"related_works":["https://openalex.org/W4415030924","https://openalex.org/W4414014501","https://openalex.org/W4410122696","https://openalex.org/W4411211423","https://openalex.org/W7154589277","https://openalex.org/W4414185713","https://openalex.org/W7096979558","https://openalex.org/W4391840390","https://openalex.org/W4395443445","https://openalex.org/W7216836073"],"abstract_inverted_index":{"Information":[0],"Retrieval":[1],"(IR)":[2],"has":[3],"undergone":[4],"a":[5,71,99,123,131,220],"profound":[6],"transformation":[7],"in":[8,206,234],"the":[9,88,161,178,189,197,226,237],"field":[10],"of":[11,66,90,102,126,134,153,180,192,225,239],"Natural":[12],"Language":[13,31],"Processing":[14],"(NLP),":[15],"shifting":[16],"from":[17,41],"traditional":[18],"keyword-based":[19],"approaches":[20],"to":[21,27,79,137,214],"neural":[22],"architectures":[23],"and,":[24],"more":[25,60],"recently,":[26],"advanced":[28],"generative":[29,112],"Large":[30],"Models":[32],"(LLMs).":[33],"Transformer-based":[34],"models":[35],"such":[36,166],"as":[37,167,182],"Bidirectional":[38],"Encoder":[39],"Representations":[40],"Transformers":[42],"(BERT)":[43],"have":[44],"substantially":[45],"improved":[46],"semantic":[47],"understanding":[48],"and":[49,59,83,117,129,141,151,169,177,202,217,222,230],"retrieval":[50,76,109,113,204],"accuracy":[51],"by":[52,74],"enabling":[53],"contextualized":[54],"embeddings,":[55],"deeper":[56],"interaction":[57],"modeling,":[58],"effective":[61],"ranking":[62],"mechanisms.":[63],"The":[64],"rise":[65],"Retrieval-Augmented":[67],"Generation":[68],"(RAG)":[69],"represents":[70],"significant":[72],"development":[73],"integrating":[75],"with":[77,94,219],"generation":[78],"produce":[80],"factually-grounded,":[81],"context-aware,":[82],"explainable":[84],"outputs,":[85],"while":[86],"reducing":[87],"likelihood":[89],"hallucinations":[91],"commonly":[92],"associated":[93],"LLMs.":[95],"This":[96,211],"survey":[97,162],"provides":[98],"comprehensive":[100],"review":[101],"modern":[103],"IR":[104,127,235],"techniques,":[105],"focusing":[106],"on":[107],"BERT-based":[108],"models,":[110],"emerging":[111,164],"frameworks,":[114],"evaluation":[115,155],"methodologies,":[116],"key":[118],"application":[119],"domains.":[120],"We":[121],"provide":[122,215],"structured":[124],"taxonomy":[125],"methods":[128],"conduct":[130],"comparative":[132],"analysis":[133],"state-of-the-art":[135],"research":[136,232],"highlight":[138],"performance":[139],"trends":[140],"methodological":[142],"distinctions.":[143],"Ongoing":[144],"challenges,":[145],"including":[146],"scalability,":[147],"computational":[148],"efficiency,":[149],"interpretability,":[150],"limitations":[152],"current":[154,228],"benchmarks,":[156],"are":[157],"critically":[158],"discussed.":[159],"Additionally,":[160],"explores":[163],"directions":[165],"multimodal":[168],"cross-modal":[170],"retrieval,":[171,176],"hybrid":[172],"dense-sparse":[173],"architectures,":[174],"knowledge-graph-enhanced":[175],"integration":[179],"LLMs":[181],"unified":[183],"retriever-generator":[184],"systems.":[185],"These":[186],"advancements":[187],"illustrate":[188],"rapid":[190],"evolution":[191],"IR.":[193],"They":[194],"also":[195],"underscore":[196],"need":[198],"for":[199],"adaptive,":[200],"reliable,":[201],"transparent":[203],"solutions":[205],"increasingly":[207],"complex":[208],"information":[209],"environments.":[210],"work":[212],"aims":[213],"researchers":[216],"practitioners":[218],"clear":[221],"organized":[223],"overview":[224],"evolution,":[227],"landscape,":[229],"future":[231],"opportunities":[233],"within":[236],"era":[238],"LLM-driven":[240],"NLP.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-12-05T00:00:00"}
