{"id":"https://openalex.org/W7127049495","doi":"https://doi.org/10.28991/esj-2026-010-01-09","title":"Structure-Aware Chunking for Complex Tables in Retrieval-Augmented Generation Systems","display_name":"Structure-Aware Chunking for Complex Tables in Retrieval-Augmented Generation Systems","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127049495","doi":"https://doi.org/10.28991/esj-2026-010-01-09"},"language":"en","primary_location":{"id":"doi:10.28991/esj-2026-010-01-09","doi":"https://doi.org/10.28991/esj-2026-010-01-09","is_oa":true,"landing_page_url":"https://doi.org/10.28991/esj-2026-010-01-09","pdf_url":"https://www.ijournalse.org/index.php/ESJ/article/download/3380/976","source":{"id":"https://openalex.org/S4210232528","display_name":"Emerging Science Journal","issn_l":"2610-9182","issn":["2610-9182"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Emerging Science Journal","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijournalse.org/index.php/ESJ/article/download/3380/976","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124743014","display_name":"Xin-Kuang Koay","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Xin-Kuang Koay","raw_affiliation_strings":["1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082947941","display_name":"Lee-Yeng Ong","orcid":"https://orcid.org/0000-0003-4749-3490","observed_orcids":["https://orcid.org/0000-0003-4749-3490"]},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lee-Yeng Ong","raw_affiliation_strings":["1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450"],"raw_orcid":"https://orcid.org/0000-0003-4749-3490","affiliations":[{"raw_affiliation_string":"1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104337216","display_name":"Pey-Yun Goh","orcid":"https://orcid.org/0000-0003-2060-3223","observed_orcids":["https://orcid.org/0000-0003-2060-3223"]},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Pey-Yun Goh","raw_affiliation_strings":["1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450"],"raw_orcid":"https://orcid.org/0000-0003-2060-3223","affiliations":[{"raw_affiliation_string":"1) Faculty of Information Science and Technology, Multimedia University, Malacca 75450, Malaysia. 2) Centre for Advanced Analytics, CoE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka 75450","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173029219"],"apc_list":{"value":40,"currency":"USD","value_usd":40},"apc_paid":{"value":40,"currency":"USD","value_usd":40},"fwci":4.1854,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93728886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"10","issue":"1","first_page":"184","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9315999746322632,"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":0.9315999746322632,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04010000079870224,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.005400000140070915,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.953000009059906},{"id":"https://openalex.org/keywords/table-extraction","display_name":"table extraction","score":0.6819999814033508},{"id":"https://openalex.org/keywords/camelot","display_name":"Camelot","score":0.7940000295639038},{"id":"https://openalex.org/keywords/scientific-information-retrieval","display_name":"scientific information retrieval","score":0.5799999833106995},{"id":"https://openalex.org/keywords/ragas-evaluation","display_name":"RAGAS evaluation","score":0.7699999809265137},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.652999997138977}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8848000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6427000164985657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5995000004768372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.5541999936103821},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.28991/esj-2026-010-01-09","doi":"https://doi.org/10.28991/esj-2026-010-01-09","is_oa":true,"landing_page_url":"https://doi.org/10.28991/esj-2026-010-01-09","pdf_url":"https://www.ijournalse.org/index.php/ESJ/article/download/3380/976","source":{"id":"https://openalex.org/S4210232528","display_name":"Emerging Science Journal","issn_l":"2610-9182","issn":["2610-9182"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Emerging Science Journal","raw_type":"journal-article"},{"id":"pmh:oai:shdl.mmu.edu.my:15426","doi":null,"is_oa":false,"landing_page_url":"https://shdl.mmu.edu.my/15426/1/9%20%284%29.pdf","pdf_url":"https://shdl.mmu.edu.my/15426/1/9%20%284%29.pdf","source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.28991/esj-2026-010-01-09","doi":"https://doi.org/10.28991/esj-2026-010-01-09","is_oa":true,"landing_page_url":"https://doi.org/10.28991/esj-2026-010-01-09","pdf_url":"https://www.ijournalse.org/index.php/ESJ/article/download/3380/976","source":{"id":"https://openalex.org/S4210232528","display_name":"Emerging Science Journal","issn_l":"2610-9182","issn":["2610-9182"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Emerging Science Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality education","score":0.6164000034332275,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127049495.pdf","grobid_xml":"https://content.openalex.org/works/W7127049495.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2909570148","https://openalex.org/W3027879771","https://openalex.org/W3039017601","https://openalex.org/W3155807546","https://openalex.org/W3217518891","https://openalex.org/W4214970283","https://openalex.org/W4221163901","https://openalex.org/W4385967979","https://openalex.org/W4387156782","https://openalex.org/W4389524107","https://openalex.org/W4389984066","https://openalex.org/W4391212494","https://openalex.org/W4391244683","https://openalex.org/W4391709255","https://openalex.org/W4402670856","https://openalex.org/W4402704461","https://openalex.org/W4403570046","https://openalex.org/W4403570188","https://openalex.org/W4403852133","https://openalex.org/W4404573334","https://openalex.org/W4404648975","https://openalex.org/W4404782124","https://openalex.org/W4406316625","https://openalex.org/W4406461112","https://openalex.org/W4407806367","https://openalex.org/W4411113004","https://openalex.org/W4412945697","https://openalex.org/W4414588358","https://openalex.org/W4415796951","https://openalex.org/W4416574656","https://openalex.org/W4416905789","https://openalex.org/W4417300102","https://openalex.org/W7081646043"],"related_works":["https://openalex.org/W7204685018","https://openalex.org/W7164044578","https://openalex.org/W4417510283","https://openalex.org/W7223135082","https://openalex.org/W4416157850","https://openalex.org/W7160288422","https://openalex.org/W4410359314","https://openalex.org/W7128710378","https://openalex.org/W4417095403","https://openalex.org/W4411544882"],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"is":[3,120,180],"a":[4,66,190],"hybrid":[5],"method":[6,119],"that":[7,96,139,172],"combines":[8],"information":[9],"retrieval":[10,153],"with":[11,39,81],"large":[12],"language":[13],"models":[14],"to":[15,31,182],"generate":[16,32],"context-aware,":[17],"factually":[18],"grounded":[19],"responses.":[20,37],"However,":[21],"the":[22,123,140,144,161],"RAG":[23,194],"system":[24],"relies":[25],"heavily":[26],"on":[27],"well-structured":[28],"input":[29],"data":[30],"accurate":[33],"and":[34,52,59,109,126,134,150,155,177],"contextually":[35],"relevant":[36],"Documents":[38],"complex":[40,198],"table":[41,90],"layouts":[42],"pose":[43],"significant":[44],"challenges,":[45],"as":[46],"most":[47],"chunking":[48,69,135,178],"strategies":[49],"are":[50],"text-centric":[51],"often":[53],"overlook":[54],"table-rich":[55,187],"documents":[56,76],"containing":[57,77],"multi-column":[58],"multi-row":[60,79],"structures.":[61],"Hence,":[62],"this":[63],"study":[64,170],"proposes":[65],"customized":[67,94],"structure-aware":[68],"framework":[70,85,125],"specifically":[71],"designed":[72],"for":[73,88,193],"university":[74],"course":[75],"multi-column,":[78],"tables":[80],"nested":[82],"headers.":[83],"The":[84,117],"employs":[86],"Camelot":[87],"high-fidelity":[89],"extraction,":[91],"followed":[92],"by":[93,101],"logic":[95],"constructs":[97],"semantically":[98],"coherent":[99],"chunks":[100],"preserving":[102],"academic":[103,167],"term,":[104],"subject":[105],"name,":[106],"credit":[107],"hour,":[108],"category.":[110],"This":[111,169],"prevents":[112],"semantic":[113,184],"fragmentation":[114],"during":[115],"retrieval.":[116],"proposed":[118,141],"evaluated":[121],"using":[122,131],"RAGAS":[124],"compared":[127],"against":[128],"several":[129],"baselines":[130],"standard":[132],"parsing":[133,175],"techniques.":[136],"Results":[137],"show":[138],"approach":[142],"achieves":[143],"highest":[145],"answer":[146],"accuracy":[147],"of":[148],"0.73":[149],"substantially":[151],"improves":[152],"relevance":[154],"contextual":[156],"precision.":[157],"These":[158],"findings":[159],"demonstrate":[160],"framework\u2019s":[162],"effectiveness":[163],"in":[164,186,196],"handling":[165],"structure-dependent":[166],"queries.":[168],"highlights":[171],"ensuring":[173],"both":[174],"quality":[176],"strategy":[179],"essential":[181],"retain":[183],"relationships":[185],"documents,":[188],"offering":[189],"practical":[191],"improvement":[192],"systems":[195],"structurally":[197],"scenarios.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-02-03T00:00:00"}