{"id":"https://openalex.org/W7212197978","doi":null,"title":"A HYBRID RULE-BASED AND LARGE LANGUAGE MODEL FRAMEWORK FOR EXTRACTING ACRONYM\u2013DEFINITION PAIRS FROM SCIENTIFIC LITERATURE","display_name":"A HYBRID RULE-BASED AND LARGE LANGUAGE MODEL FRAMEWORK FOR EXTRACTING ACRONYM\u2013DEFINITION PAIRS FROM SCIENTIFIC LITERATURE","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212197978"},"language":"en","primary_location":{"id":"pmh:oai:rdw.rowan.edu:etd-4585","doi":null,"is_oa":true,"landing_page_url":"https://rdw.rowan.edu/etd/3579","pdf_url":"https://rdw.rowan.edu/cgi/viewcontent.cgi?article=4585&context=etd","source":{"id":"https://openalex.org/S4377196130","display_name":"Rowan Digitals Works (Rowan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I44265643","host_organization_name":"Rowan University","host_organization_lineage":["https://openalex.org/I44265643"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses and Dissertations","raw_type":"thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://rdw.rowan.edu/cgi/viewcontent.cgi?article=4585&context=etd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151194912","display_name":"Petro Skrypnyk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Skrypnyk, Petro","raw_affiliation_strings":["Rowan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rowan University","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5151194912"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8105000257492065,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8105000257492065,"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/T10028","display_name":"Topic Modeling","score":0.1143999993801117,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.030500000342726707,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scientific-publications","display_name":"scientific publications","score":0.9110000133514404},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8190000057220459},{"id":"https://openalex.org/keywords/rule-based-parsing","display_name":"rule-based parsing","score":0.7170000076293945},{"id":"https://openalex.org/keywords/precision-recall-trade-off","display_name":"precision-recall trade-off","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288000226020813},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7006000280380249},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6100000143051147},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C71008984","wikidata":"https://www.wikidata.org/wiki/Q2890076","display_name":"Rigour","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:rdw.rowan.edu:etd-4585","doi":null,"is_oa":true,"landing_page_url":"https://rdw.rowan.edu/etd/3579","pdf_url":"https://rdw.rowan.edu/cgi/viewcontent.cgi?article=4585&context=etd","source":{"id":"https://openalex.org/S4377196130","display_name":"Rowan Digitals Works (Rowan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I44265643","host_organization_name":"Rowan University","host_organization_lineage":["https://openalex.org/I44265643"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses and Dissertations","raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:rdw.rowan.edu:etd-4585","doi":null,"is_oa":true,"landing_page_url":"https://rdw.rowan.edu/etd/3579","pdf_url":"https://rdw.rowan.edu/cgi/viewcontent.cgi?article=4585&context=etd","source":{"id":"https://openalex.org/S4377196130","display_name":"Rowan Digitals Works (Rowan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I44265643","host_organization_name":"Rowan University","host_organization_lineage":["https://openalex.org/I44265643"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses and Dissertations","raw_type":"thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212197978.pdf","grobid_xml":"https://content.openalex.org/works/W7212197978.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W1484050045","https://openalex.org/W1603719052","https://openalex.org/W1933390880","https://openalex.org/W2024940313","https://openalex.org/W2078483536","https://openalex.org/W2095437242","https://openalex.org/W2102269881","https://openalex.org/W2117897510","https://openalex.org/W2120609672","https://openalex.org/W2170505850","https://openalex.org/W2626778328","https://openalex.org/W2905534339","https://openalex.org/W2953097228","https://openalex.org/W2963341956","https://openalex.org/W2970771982","https://openalex.org/W3021095356","https://openalex.org/W3030163527","https://openalex.org/W3044940880","https://openalex.org/W3118227682","https://openalex.org/W3134741912","https://openalex.org/W4238015202","https://openalex.org/W4241727697","https://openalex.org/W4384918448","https://openalex.org/W4391836235","https://openalex.org/W4404239715","https://openalex.org/W4405033884"],"related_works":["https://openalex.org/W2132685569","https://openalex.org/W1542243371","https://openalex.org/W2148154845","https://openalex.org/W7095843866","https://openalex.org/W2134189109","https://openalex.org/W7098898087","https://openalex.org/W2045931042","https://openalex.org/W90158706","https://openalex.org/W7127941777","https://openalex.org/W1480871907"],"abstract_inverted_index":{"Authors":[0],"of":[1,80,178,227,246,253],"scientific":[2,42,184],"papers":[3,181],"rely":[4],"heavily":[5],"on":[6,61,135,149],"acronyms":[7],"and":[8,21,26,31,115,145,148,164,189,208,211,243,249],"often":[9],"use":[10],"them":[11],"without":[12],"defining":[13],"them,":[14],"making":[15],"the":[16,69,72,81,154,160,165,204,214,250],"literature":[17],"harder":[18],"to":[19,93,258],"read":[20],"index.":[22],"This":[23,195],"thesis":[24],"develops":[25],"evaluates":[27],"a":[28,54,58,86,173],"hybrid":[29,236],"rule-based":[30],"large":[32],"language":[33],"model":[34,124],"(LLM)":[35],"framework":[36,84],"that":[37,52,67,198,203,212],"extracts":[38],"acronym\u2013definition":[39,247],"pairs":[40],"from":[41,90],"PDF":[43,91,162],"documents.":[44],"It":[45,96],"extends":[46],"an":[47,169,218],"earlier":[48],"Rowan":[49],"University":[50],"system":[51,65],"combined":[53],"regular-expression":[55],"parser":[56,70,155,166,215],"with":[57,192,217,238],"single":[59],"LLM":[60,73,99,131,158,219],"200":[62,180],"papers.":[63],"That":[64],"showed":[66],"neither":[68],"nor":[71],"alone":[74],"is":[75,85,133],"sufficient":[76],"for":[77,222],"accurate":[78,242],"extraction":[79,245,252],"pairs.":[82],"The":[83],"fully":[87],"automated":[88],"pipeline":[89],"input":[92,137],"scored":[94],"results.":[95],"compares":[97],"four":[98,183],"providers":[100],"through":[101],"their":[102],"lightweight,":[103],"low-cost":[104],"tier":[105],"models":[106],"(GPT-4o":[107],"mini,":[108],"Gemini":[109],"2.0":[110],"Flash,":[111],"Claude":[112],"Haiku":[113],"4.5,":[114],"Kimi":[116],"K2.5)":[117],"under":[118],"identical":[119],"prompts,":[120],"so":[121],"differences":[122],"reflect":[123],"capability":[125],"rather":[126],"than":[127],"prompt":[128],"design.":[129],"Each":[130],"provider":[132],"evaluated":[134],"three":[136],"types":[138],"(the":[139],"raw":[140,161],"PDF,":[141],"unprocessed":[142],"extracted":[143],"text,":[144],"preprocessed":[146],"text)":[147],"seven":[150],"method":[151],"configurations":[152],"spanning":[153],"alone,":[156,159],"each":[157],"path,":[163],"refined":[167],"by":[168],"LLM.":[170],"Evaluation":[171],"against":[172],"manually":[174],"annotated":[175],"ground":[176],"truth":[177],"about":[179,254],"across":[182],"domains":[185],"reports":[186],"precision,":[187,202],"recall,":[188],"F1":[190],"score":[191],"confidence":[193],"intervals.":[194],"evaluation":[196],"confirms":[197,232],"preprocessing":[199,240],"substantially":[200],"improves":[201],"LLMs":[205],"balance":[206],"precision":[207,221],"recall":[209],"differently,":[210],"refining":[213],"output":[216],"trades":[220],"recall.":[223],"An":[224],"additional":[225],"comparison":[226],"around":[228],"800":[229],"unannotated":[230],"documents":[231,256],"these":[233],"findings.":[234],"A":[235],"design":[237],"careful":[239],"yields":[241],"scalable":[244],"pairs,":[248],"production":[251],"10,000":[255],"remains":[257],"be":[259],"run.":[260]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-11T00:00:00"}