{"id":"https://openalex.org/W4393701591","doi":"https://doi.org/10.5281/zenodo.10231085","title":"Synthetic dataset for end-to-end Relation Extraction of relationships between Organisms and Natural-Products with Vicuna-13b-v1.5","display_name":"Synthetic dataset for end-to-end Relation Extraction of relationships between Organisms and Natural-Products with Vicuna-13b-v1.5","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4393701591","doi":"https://doi.org/10.5281/zenodo.10231085"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10231085","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10231085","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10231085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076973287","display_name":"Maxime Delmas","orcid":"https://orcid.org/0000-0002-9352-0624"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Delmas, Maxime","raw_affiliation_strings":["Idiap Research Institute"],"raw_orcid":"https://orcid.org/0000-0002-9352-0624","affiliations":[{"raw_affiliation_string":"Idiap Research Institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016561885","display_name":"Magdalena Wysocka","orcid":"https://orcid.org/0000-0003-2216-5597"},"institutions":[{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wysocka, Magdalena","raw_affiliation_strings":["dECMT, Cancer Research UK Manchester Institue; The university of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"dECMT, Cancer Research UK Manchester Institue; The university of Manchester","institution_ids":["https://openalex.org/I4210129527"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053978668","display_name":"Andr\u00e9 Freitas","orcid":"https://orcid.org/0000-0002-4430-4837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freitas, Andr\u00e9","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4430-4837","affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.8190000057220459,"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"}},"topics":[{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.8190000057220459,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5813555121421814},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5517961382865906},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5207607746124268},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5177397131919861},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.4116438627243042},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.30839401483535767},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24661484360694885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.21541649103164673},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.17863479256629944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17566010355949402},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1459321677684784},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.11544784903526306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10397696495056152}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5813555121421814},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5517961382865906},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5207607746124268},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5177397131919861},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.4116438627243042},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.30839401483535767},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24661484360694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.21541649103164673},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.17863479256629944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17566010355949402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1459321677684784},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.11544784903526306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10397696495056152},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10231085","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10231085","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10231085","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10231085","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4293268064","https://openalex.org/W2218833963","https://openalex.org/W2964709658","https://openalex.org/W4240479622","https://openalex.org/W4246369259","https://openalex.org/W2151749779","https://openalex.org/W1914800454","https://openalex.org/W2497297478"],"abstract_inverted_index":{"A":[0],"new":[1,16,52],"synthetic":[2,31],"dataset":[3,17,53,71,87],"(training/validation)":[4],"for":[5,43],"end-to-end":[6],"Relation":[7],"Extraction":[8],"of":[9,39],"relationships":[10],"between":[11],"Organisms":[12],"and":[13,79],"Natural-Products.":[14],"The":[15,51,70,86],"was":[18,54,88],"generated":[19,89],"using":[20,90],"Vicuna-13b-v1.5,":[21],"derived":[22],"from":[23],"LLaMA":[24,48],"2.":[25],"Like":[26],"the":[27,29,37,40,46,58,68,76,83,91,97],"model,":[28],"produced":[30],"data":[32],"are":[33],"also":[34],"submitted":[35],"to":[36],"License":[38],"model":[41],"used":[42],"generation,":[44],"see":[45],"original":[47],"2":[49],"license.":[50],"created":[55],"based":[56],"on":[57],"top-1000":[59],"(per":[60],"biological":[61],"kingdom)":[62],"LOTUS":[63],"literature":[64],"references":[65],"extracted":[66],"with":[67],"GME-sampler.":[69],"contains":[72],"10,405":[73],"items":[74,81],"in":[75,82,96],"training":[77],"set":[78],"547":[80],"validation":[84],"set.":[85],"same":[92],"protocol":[93],"as":[94],"described":[95],"article.":[98]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
