{"id":"https://openalex.org/W4410356886","doi":"https://doi.org/10.1145/3672608.3707858","title":"Improving Natural Product Knowledge Extraction from Academic Literature with Enhanced PDF Text Extraction and Large Language Models","display_name":"Improving Natural Product Knowledge Extraction from Academic Literature with Enhanced PDF Text Extraction and Large Language Models","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356886","doi":"https://doi.org/10.1145/3672608.3707858"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707858","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","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/A5087084192","display_name":"Paulo Ricardo Viviurka do Carmo","orcid":"https://orcid.org/0000-0002-8550-4368"},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Paulo Viviurka do Carmo","raw_affiliation_strings":["HTWK Faculty of Computer Science AKSW, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"HTWK Faculty of Computer Science AKSW, Leipzig, Germany","institution_ids":["https://openalex.org/I147765834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031939880","display_name":"Marcos Paulo Silva G\u00f4lo","orcid":"https://orcid.org/0000-0002-9093-8195"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Paulo Silva G\u00f4lo","raw_affiliation_strings":["Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I4210131883","https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117539772","display_name":"Jonas Gwozdz","orcid":null},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Gwozdz","raw_affiliation_strings":["HTWK Faculty of Computer Science AKSW, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"HTWK Faculty of Computer Science AKSW, Leipzig, Germany","institution_ids":["https://openalex.org/I147765834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080498781","display_name":"Edgard Marx","orcid":"https://orcid.org/0000-0002-3111-9405"},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Edgard Marx","raw_affiliation_strings":["HTWK Faculty of Computer Science AKSW, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"HTWK Faculty of Computer Science AKSW, Leipzig, Germany","institution_ids":["https://openalex.org/I147765834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103168466","display_name":"Ricardo Marcondes Marcacini","orcid":"https://orcid.org/0000-0002-2309-3487"},"institutions":[{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ricardo Marcondes Marcacini","raw_affiliation_strings":["Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I4210131883","https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087084192"],"corresponding_institution_ids":["https://openalex.org/I147765834"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05235506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.735382080078125},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6966094970703125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5609294176101685},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48103243112564087},{"id":"https://openalex.org/keywords/natural-product","display_name":"Natural product","score":0.4281119704246521},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.42425963282585144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38537082076072693},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34201568365097046},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.14541929960250854},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12167859077453613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1090444028377533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735382080078125},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6966094970703125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5609294176101685},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48103243112564087},{"id":"https://openalex.org/C2779396153","wikidata":"https://www.wikidata.org/wiki/Q901227","display_name":"Natural product","level":2,"score":0.4281119704246521},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.42425963282585144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38537082076072693},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34201568365097046},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.14541929960250854},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12167859077453613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1090444028377533},{"id":"https://openalex.org/C71240020","wikidata":"https://www.wikidata.org/wiki/Q186011","display_name":"Stereochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707858","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1491110638","https://openalex.org/W2038880450","https://openalex.org/W2154851992","https://openalex.org/W2155590214","https://openalex.org/W2187089797","https://openalex.org/W2551706664","https://openalex.org/W2739691438","https://openalex.org/W2743104969","https://openalex.org/W2962756421","https://openalex.org/W2970641574","https://openalex.org/W3011366455","https://openalex.org/W3080649566","https://openalex.org/W3104097132","https://openalex.org/W4206804986","https://openalex.org/W4285194159","https://openalex.org/W4306317466","https://openalex.org/W4323928803","https://openalex.org/W4327928788","https://openalex.org/W4391136507","https://openalex.org/W6854692045","https://openalex.org/W6893753706"],"related_works":["https://openalex.org/W2968368302","https://openalex.org/W4400618531","https://openalex.org/W2414309485","https://openalex.org/W1851279709","https://openalex.org/W2731175684","https://openalex.org/W3137353528","https://openalex.org/W3148197098","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"The":[0,24,86,107],"biodiversity":[1],"of":[2,9,14,93,142,168],"tropical":[3],"environments":[4],"offers":[5],"a":[6,89],"rich":[7],"variety":[8],"species":[10],"for":[11,41,70,83,104,126,138],"the":[12,67,84,94,105,123,127,158,177],"process":[13],"finding":[15],"new":[16],"drugs":[17],"based":[18],"on":[19,66,146,176],"Natural":[20,27,71],"Products.":[21],"Databases":[22],"like":[23,65],"Brazilian":[25],"Biodiversity":[26],"Products":[28],"Database":[29],"(NUBBEDB),":[30],"where":[31],"they":[32],"hold":[33],"compounds":[34,54],"and":[35,96,152],"characteristics":[36],"about":[37,53],"them,":[38],"are":[39,47],"important":[40,81],"computational":[42],"assistance.":[43],"However,":[44],"these":[45],"databases":[46],"difficult":[48],"to":[49],"update":[50],"since":[51],"data":[52],"is":[55,79,112],"mostly":[56],"published":[57],"in":[58,165],"academic":[59],"papers.":[60],"Therefore,":[61],"automatic":[62],"Knowledge":[63,73,90,100],"Extraction":[64,74],"state-of-the-art":[68,164],"Benchmark":[69],"Product":[72],"from":[75,110,150],"Academic":[76],"Literature":[77],"(NatUKE),":[78],"an":[80,113],"task":[82],"field.":[85],"dataset":[87],"uses":[88,118],"Graph":[91,101],"version":[92],"NUBBEDB":[95],"it":[97],"evaluates":[98],"different":[99],"Embedding":[102],"models":[103,121],"task.":[106],"best":[108],"performer":[109],"NatUKE":[111],"embedding":[114,125],"propagation":[115],"model":[116],"that":[117,129],"pre-trained":[119],"language":[120],"as":[122,157],"start-up":[124,159],"nodes":[128],"contain":[130],"text":[131,148],"data.":[132],"This":[133],"work":[134],"investigates":[135],"two":[136],"avenues":[137],"increasing":[139],"performance":[140,175],"out":[141,167],"NatUKE.":[143],"We":[144],"focused":[145],"better":[147],"extraction":[149],"PDFs":[151],"using":[153],"Large":[154],"Language":[155],"Models":[156],"embeddings.":[160],"Our":[161],"results":[162],"surpassed":[163],"3":[166],"5":[169],"extracted":[170],"features":[171],"while":[172],"maintaining":[173],"competitive":[174],"remaining":[178],"features.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}