{"id":"https://openalex.org/W4393798499","doi":"https://doi.org/10.5281/zenodo.8422294","title":"Synthetic datasets for end-to-end Relation Extraction of relationships between Organisms and Natural-Products","display_name":"Synthetic datasets for end-to-end Relation Extraction of relationships between Organisms and Natural-Products","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4393798499","doi":"https://doi.org/10.5281/zenodo.8422294"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.8422294","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8422294","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.8422294","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":"Maxime Delmas","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/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"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":"Magdalena Wysocka","raw_affiliation_strings":["dECMT, Cancer Research UK Manchester Institute; The University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"dECMT, Cancer Research UK Manchester Institute; The University of Manchester","institution_ids":["https://openalex.org/I28407311","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":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Andre Freitas","raw_affiliation_strings":["The University of Manchester; Idiap Research Institute"],"raw_orcid":"https://orcid.org/0000-0002-4430-4837","affiliations":[{"raw_affiliation_string":"The University of Manchester; Idiap Research Institute","institution_ids":["https://openalex.org/I28407311","https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.8070999979972839,"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":0.8070999979972839,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7944999933242798,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.7360000014305115,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6594815850257874},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5597960948944092},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5506658554077148},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5175389647483826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3262590765953064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.28959551453590393},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.25578606128692627},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.21315908432006836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19628238677978516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1886959969997406},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1507616937160492},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.08428239822387695}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6594815850257874},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5597960948944092},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5506658554077148},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5175389647483826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3262590765953064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28959551453590393},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.25578606128692627},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21315908432006836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19628238677978516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1886959969997406},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1507616937160492},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.08428239822387695}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.8422294","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8422294","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.8422294","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8422294","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W3179968364","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793","https://openalex.org/W4238204885"],"abstract_inverted_index":{"Synthetic":[0],"datasets":[1,14,38,65,89],"(training/validation)":[2],"for":[3,17,111],"end-to-end":[4],"Relation":[5],"Extraction":[6],"of":[7,36,66,81,107],"relationships":[8],"between":[9],"Organisms":[10],"and":[11,83],"Natural-Products.":[12],"The":[13,42],"are":[15,39,101],"provided":[16],"reproducibility":[18],"purposes,":[19],"but,":[20],"can":[21],"also":[22,102],"be":[23],"used":[24,46,110],"to":[25,52,104],"train":[26],"new":[27],"models.":[28],"As":[29],"in":[30,47],"the":[31,48,53,61,84,95,97,105,108,114,123],"corresponding":[32],"article,":[33],"3":[34],"subtypes":[35],"synthetic":[37,99],"provided:":[40],"Diversity-synt:":[41],"seed":[43,75],"literature":[44,76],"references":[45],"generation":[49],"process":[50],"correspond":[51],"top-500":[54],"extracted":[55],"items":[56],"per":[57],"biological":[58],"kingdoms":[59],"using":[60,72],"GME-sampler.":[62],"Random-synt:":[63],"5":[64,85],"equivalent":[67],"sizes":[68],"as":[69],"Diversity-synt,":[70],"but":[71],"randomly":[73],"sampled":[74],"references.":[77],"Extended-synt:":[78],"A":[79],"merge":[80],"Diversity-synt":[82],"Random-synt":[86],"datasets.":[87],"All":[88,131],"were":[90],"produced":[91,98],"with":[92],"Vicuna-13b-v1.3.":[93],"Like":[94],"model,":[96],"data":[100],"submitted":[103],"License":[106],"model":[109,117],"generation,":[112],"see":[113],"original":[115],"LLaMA":[116,119,124],"card.":[118],"is":[120],"licensed":[121],"under":[122],"License,":[125],"Copyright":[126],"(c)":[127],"Meta":[128],"Platforms,":[129],"Inc.":[130],"Rights":[132],"Reserved.":[133]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}