{"id":"https://openalex.org/W2970090041","doi":"https://doi.org/10.18653/v1/w19-5013","title":"Query selection methods for automated corpora construction with a use case in food-drug interactions","display_name":"Query selection methods for automated corpora construction with a use case in food-drug interactions","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970090041","doi":"https://doi.org/10.18653/v1/w19-5013","mag":"2970090041"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5013","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5013","pdf_url":"https://www.aclweb.org/anthology/W19-5013.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5013.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049680489","display_name":"Georgeta Bordea","orcid":"https://orcid.org/0000-0001-9921-8234"},"institutions":[{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"funder","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I4210106115","display_name":"Bordeaux Population Health","ror":"https://ror.org/00xzzba89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I15057530","https://openalex.org/I154526488","https://openalex.org/I4210106115"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Georgeta Bordea","raw_affiliation_strings":["Univ. Bordeaux, Inserm UMR 1219, Bordeaux Population Health, team ERIAS, Bordeaux, France","Bordeaux population health"],"affiliations":[{"raw_affiliation_string":"Univ. Bordeaux, Inserm UMR 1219, Bordeaux Population Health, team ERIAS, Bordeaux, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I15057530","https://openalex.org/I4210106115"]},{"raw_affiliation_string":"Bordeaux population health","institution_ids":["https://openalex.org/I4210106115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047331068","display_name":"Tsanta Randriatsitohaina","orcid":"https://orcid.org/0000-0003-3630-6717"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tsanta Randriatsitohaina","raw_affiliation_strings":["LIMSI, CNRS UPR 3251, Universit Paris-Saclay, Orsay, France","Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS UPR 3251, Universit Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090250858","display_name":"Fleur Mougin","orcid":"https://orcid.org/0000-0002-7436-3010"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"funder","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I4210106115","display_name":"Bordeaux Population Health","ror":"https://ror.org/00xzzba89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I15057530","https://openalex.org/I154526488","https://openalex.org/I4210106115"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fleur Mougin","raw_affiliation_strings":["Univ. Bordeaux, Inserm UMR 1219, Bordeaux Population Health, team ERIAS, Bordeaux, France","Bordeaux population health"],"affiliations":[{"raw_affiliation_string":"Univ. Bordeaux, Inserm UMR 1219, Bordeaux Population Health, team ERIAS, Bordeaux, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I15057530","https://openalex.org/I4210106115"]},{"raw_affiliation_string":"Bordeaux population health","institution_ids":["https://openalex.org/I4210106115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007781745","display_name":"Natalia Grabar","orcid":"https://orcid.org/0000-0002-0237-4554"},"institutions":[{"id":"https://openalex.org/I4210087136","display_name":"Savoirs, Textes, Langage","ror":"https://ror.org/003fs1j49","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4210087136","https://openalex.org/I4210150854"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Natalia Grabar","raw_affiliation_strings":["CNRS UMR 8163 -STL -Savoirs Textes Langage, Univ. Lille, Lille, France","Savoirs, Textes, Langage (STL) - UMR 8163"],"affiliations":[{"raw_affiliation_string":"CNRS UMR 8163 -STL -Savoirs Textes Langage, Univ. Lille, Lille, France","institution_ids":["https://openalex.org/I4210087136","https://openalex.org/I2279609970","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Savoirs, Textes, Langage (STL) - UMR 8163","institution_ids":["https://openalex.org/I4210087136"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014683954","display_name":"Thierry Hamon","orcid":"https://orcid.org/0000-0002-1521-4875"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thierry Hamon","raw_affiliation_strings":["LIMSI, CNRS UPR 3251, Universit Paris-Saclay, Orsay, France","Universit Paris 13, Sorbonne Paris Cit, Villfetaneuse, France","Universit\u00e9 Paris 13","Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS UPR 3251, Universit Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit Paris 13, Sorbonne Paris Cit, Villfetaneuse, France","institution_ids":["https://openalex.org/I4210091437","https://openalex.org/I4210091279"]},{"raw_affiliation_string":"Universit\u00e9 Paris 13","institution_ids":["https://openalex.org/I4210091279"]},{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049680489"],"corresponding_institution_ids":["https://openalex.org/I15057530","https://openalex.org/I154526488","https://openalex.org/I4210106115"],"apc_list":null,"apc_paid":null,"fwci":0.1718,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53035154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9933000206947327,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9933000206947327,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9879000186920166,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9764000177383423,"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":0.8237454295158386},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6488884091377258},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5428152084350586},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5423614978790283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364876985549927},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5128076672554016},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4791940152645111},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.44419628381729126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41705700755119324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4157297611236572},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3836474120616913},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3614761531352997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237454295158386},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6488884091377258},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5428152084350586},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5423614978790283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364876985549927},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5128076672554016},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4791940152645111},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.44419628381729126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41705700755119324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4157297611236572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3836474120616913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3614761531352997},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5013","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5013","pdf_url":"https://www.aclweb.org/anthology/W19-5013.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02371207v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02371207","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACL Workshop on Biomedical Natural Language Processing, Aug 2019, Florence, Italy. pp.115-124, ⟨10.18653/v1/W19-5013⟩","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/64154","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/64154","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/7627","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/7627","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Autre communication scientifique (congr\u00e8s sans actes - poster - s\u00e9minaire...)"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5013","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5013","pdf_url":"https://www.aclweb.org/anthology/W19-5013.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G2106064874","display_name":"Knowledge graph completion using Artificial Neural Networks for Herb-Drug Interaction discovery","funder_award_id":"800578","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G583963735","display_name":null,"funder_award_id":"MSCA-IF","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8332583186","display_name":"Diseases, Food-Drug Interactions","funder_award_id":"ANR-16-CE23-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970090041.pdf","grobid_xml":"https://content.openalex.org/works/W2970090041.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1508531867","https://openalex.org/W1555836061","https://openalex.org/W1794469725","https://openalex.org/W1849984936","https://openalex.org/W2046899569","https://openalex.org/W2067802667","https://openalex.org/W2103333826","https://openalex.org/W2114272534","https://openalex.org/W2129767020","https://openalex.org/W2148488766","https://openalex.org/W2396479859","https://openalex.org/W2405256399","https://openalex.org/W2512955867","https://openalex.org/W2885154548","https://openalex.org/W3010058008","https://openalex.org/W4299556548"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2383516975","https://openalex.org/W2374878784","https://openalex.org/W2147679489","https://openalex.org/W2371642785"],"abstract_inverted_index":{"In":[0],"this":[1,83],"paper,":[2],"we":[3],"address":[4],"the":[5,54,79],"problem":[6],"of":[7,13,24,62],"automatically":[8],"constructing":[9],"a":[10,21,34,74],"relevant":[11],"corpus":[12,36,61],"scientific":[14,25],"articles":[15],"about":[16],"food-drug":[17,29,63],"interactions.":[18,64],"There":[19],"is":[20,45],"growing":[22],"number":[23],"publications":[26],"that":[27,37,68,86],"describe":[28],"interactions":[30],"but":[31],"currently":[32],"building":[33],"high-coverage":[35],"can":[38],"be":[39],"used":[40],"for":[41,52,82,98],"information":[42],"extraction":[43],"purposes":[44],"not":[46],"trivial.":[47],"We":[48],"investigate":[49],"several":[50],"methods":[51,97],"automating":[53],"query":[55,99],"selection":[56,88],"process":[57],"using":[58],"an":[59],"expert-curated":[60],"Our":[65],"experiments":[66],"show":[67],"index":[69],"terms":[70],"features":[71],"along":[72],"with":[73],"decision":[75],"tree":[76],"classifier":[77],"are":[78],"best":[80],"approach":[81],"task":[84],"and":[85,90],"feature":[87],"approaches":[89],"in":[91],"particular":[92],"gain":[93],"ratio":[94],"outperform":[95],"frequencybased":[96],"selection.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}