{"id":"https://openalex.org/W4406459833","doi":"https://doi.org/10.1109/ithet61869.2024.10837640","title":"Scientific Publication Indexing and Definition Extraction Resource","display_name":"Scientific Publication Indexing and Definition Extraction Resource","publication_year":2024,"publication_date":"2024-11-06","ids":{"openalex":"https://openalex.org/W4406459833","doi":"https://doi.org/10.1109/ithet61869.2024.10837640"},"language":"en","primary_location":{"id":"doi:10.1109/ithet61869.2024.10837640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ithet61869.2024.10837640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Conference on Information Technology Based Higher Education and Training (ITHET)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049702424","display_name":"Priyanka Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Priyanka Singh","raw_affiliation_strings":["Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115904873","display_name":"Pratik Nichite","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pratik Nichite","raw_affiliation_strings":["Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055430969","display_name":"Anita Raja","orcid":"https://orcid.org/0000-0002-0735-7358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdul Basit Raja","raw_affiliation_strings":["Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045325803","display_name":"P. T. P. Sah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pranav Kumar Sah","raw_affiliation_strings":["Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009986933","display_name":"Ivan P. Yamshchikov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan P. Yamshchikov","raw_affiliation_strings":["Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Applied Sciences,Faculty of Computer Science,Würzburg-Schweinfurt,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049702424"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23766238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.998199999332428,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9969000220298767,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8012481331825256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281317710876465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5888914465904236},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5403568744659424},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.43631216883659363},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41892626881599426},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35725846886634827},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06944257020950317}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8012481331825256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281317710876465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5888914465904236},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5403568744659424},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.43631216883659363},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41892626881599426},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35725846886634827},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06944257020950317},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ithet61869.2024.10837640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ithet61869.2024.10837640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Conference on Information Technology Based Higher Education and Training (ITHET)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W1994177318","https://openalex.org/W2016951293","https://openalex.org/W2096537696","https://openalex.org/W2133857018","https://openalex.org/W2137689384","https://openalex.org/W2250803090","https://openalex.org/W2963418526","https://openalex.org/W3016492791","https://openalex.org/W4214717370","https://openalex.org/W4237783107","https://openalex.org/W4382677476","https://openalex.org/W4392002118"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"Defining":[0],"relevant":[1],"concepts":[2],"from":[3,240],"scientific":[4,40,63,71,98,167,220,265],"texts":[5],"is":[6,55,130],"always":[7],"challenging":[8],"because":[9],"of":[10,16,53,60,70,96,105,136,185,195,206,216,264],"the":[11,58,68,75,94,97,103,134,172,183,193,214],"complex":[12],"and":[13,28,38,47,65,82,90,111,121,158,182,212,221,255],"large":[14,106,262],"amount":[15,263],"information,":[17],"especially":[18],"in":[19,42,219,229],"fast-growing":[20],"disciplines.":[21,223],"We":[22],"propose":[23],"SPIDER":[24,54,92,143,173,245],"(Scientific":[25],"Publication":[26],"Indexing":[27],"Definition":[29],"Extraction":[30],"Resource),":[31],"a":[32,202,237,249,261],"tool":[33,251],"that":[34,129],"can":[35,246],"automatically":[36],"index":[37],"define":[39],"papers":[41],"portable":[43],"document":[44,108],"format":[45],"(PDF)":[46],"text":[48],"format.":[49],"The":[50,100,142,169,224],"primary":[51],"task":[52],"to":[56,109,124,164,175,242,259],"address":[57],"issue":[59],"understanding":[61],"massive":[62],"documents":[64],"further":[66,131],"improves":[67],"accessibility":[69],"information.":[72,266],"By":[73],"applying":[74],"state-of-the-art":[76,161],"natural":[77],"language":[78,162],"processing":[79],"(NLP)":[80],"techniques":[81],"self-contained":[83],"large-language":[84],"models(LLM)":[85],"such":[86,117,148,198],"as":[87,118,149,199],"Ollama,":[88],"phi3,":[89],"mistral;":[91],"increases":[93],"readability":[95],"contents.":[99],"model":[101,190],"uses":[102,145],"conversion":[104],"PDF":[107,152],"text,":[110],"then":[112],"it":[113],"applies":[114],"NLP":[115,146,156],"methods":[116],"tokenization,":[119],"stemming,":[120],"part-of-speech":[122],"tagging":[123],"create":[125],"an":[126],"accurate":[127,231],"glossary":[128],"fine-tuned":[132],"with":[133,236],"help":[135],"self-hosted":[137,186],"LLMs":[138],"for":[139,151,155,160,252],"detailed":[140],"description.":[141],"method":[144],"modules":[147],"PyPDF2":[150],"handling,":[153],"NLTK":[154],"operations,":[157],"transformers":[159],"modeling":[163],"efficiently":[165],"comprehend":[166],"articles.":[168],"paper":[170],"describes":[171],"approach":[174],"data":[176],"cleaning,":[177],"tokenizer,":[178],"stemmer,":[179],"PoS":[180],"tagger,":[181],"use":[184],"LLMs.":[187],"Potentially":[188],"this":[189],"could":[191],"benefit":[192],"enhancement":[194,205],"various":[196],"fields":[197],"speeding":[200],"up":[201],"literature":[203],"review,":[204],"educational":[207],"materials,":[208],"creating":[209],"comprehensive":[210],"glossaries,":[211],"supporting":[213],"development":[215],"knowledge-based":[217],"systems":[218],"technological":[222],"result":[225],"shows":[226],"SPIDER's":[227],"effectiveness":[228],"generating":[230],"glossaries":[232],"achieving":[233],"optimal":[234],"performance":[235],"threshold":[238],"range":[239],"0.1":[241],"0.4.":[243],"Thus,":[244],"be":[247],"considered":[248],"useful":[250],"researchers,":[253],"professors,":[254],"others":[256],"who":[257],"aim":[258],"handle":[260]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}