{"id":"https://openalex.org/W2971086334","doi":"https://doi.org/10.18653/v1/w19-5026","title":"Is artificial data useful for biomedical Natural Language Processing algorithms?","display_name":"Is artificial data useful for biomedical Natural Language Processing algorithms?","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2971086334","doi":"https://doi.org/10.18653/v1/w19-5026","mag":"2971086334"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5026","pdf_url":"https://www.aclweb.org/anthology/W19-5026.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/W19-5026.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103325843","display_name":"Zixu Wang","orcid":"https://orcid.org/0009-0006-1327-6366"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zixu Wang","raw_affiliation_strings":["Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021442709","display_name":"Julia Ive","orcid":"https://orcid.org/0000-0002-3931-3392"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julia Ive","raw_affiliation_strings":["DCS, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"DCS, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070579609","display_name":"Sumithra Velupillai","orcid":"https://orcid.org/0000-0002-4178-2980"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sumithra Velupillai","raw_affiliation_strings":["IoPPN, King's College London, UK and KTH, Sweden"],"affiliations":[{"raw_affiliation_string":"IoPPN, King's College London, UK and KTH, Sweden","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053217291","display_name":"Lucia Specia","orcid":"https://orcid.org/0000-0002-5495-3128"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucia Specia","raw_affiliation_strings":["Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103325843"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.8671,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81153457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8517704606056213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6745464205741882},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6433185338973999},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5501554012298584},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5390064716339111},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4902186989784241},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.48707178235054016},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.486172616481781},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4620937407016754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4572051167488098},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44302570819854736},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4278339147567749},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42186370491981506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4121195077896118},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3803851008415222},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2949010133743286},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12190636992454529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8517704606056213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6745464205741882},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6433185338973999},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5501554012298584},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5390064716339111},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4902186989784241},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.48707178235054016},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.486172616481781},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4620937407016754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4572051167488098},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44302570819854736},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4278339147567749},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42186370491981506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4121195077896118},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3803851008415222},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2949010133743286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12190636992454529},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-5026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5026","pdf_url":"https://www.aclweb.org/anthology/W19-5026.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"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5026","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5026","pdf_url":"https://www.aclweb.org/anthology/W19-5026.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G1525809646","display_name":null,"funder_award_id":"600398","funder_id":"https://openalex.org/F4320323807","funder_display_name":"Institut National Du Cancer"},{"id":"https://openalex.org/G291618300","display_name":null,"funder_award_id":"2015-0035","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G3456956060","display_name":null,"funder_award_id":"INCA 600398","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G511139680","display_name":null,"funder_award_id":"2015-00359","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320323807","display_name":"Institut National Du Cancer","ror":"https://ror.org/03m8vkq32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2971086334.pdf","grobid_xml":"https://content.openalex.org/works/W2971086334.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1832693441","https://openalex.org/W2005430761","https://openalex.org/W2101105183","https://openalex.org/W2101234009","https://openalex.org/W2109651326","https://openalex.org/W2130942839","https://openalex.org/W2133286915","https://openalex.org/W2133564696","https://openalex.org/W2137407193","https://openalex.org/W2154652894","https://openalex.org/W2250539671","https://openalex.org/W2293452551","https://openalex.org/W2396881363","https://openalex.org/W2741502284","https://openalex.org/W2789244308","https://openalex.org/W2797913374","https://openalex.org/W2803267010","https://openalex.org/W2805183640","https://openalex.org/W2805486818","https://openalex.org/W2885568805","https://openalex.org/W2889009749","https://openalex.org/W2889326796","https://openalex.org/W2946794439","https://openalex.org/W2963096510","https://openalex.org/W2963212250","https://openalex.org/W2963403868","https://openalex.org/W2963708445","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3098325931","https://openalex.org/W3102123817","https://openalex.org/W4289703781","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2352298027","https://openalex.org/W4319940250","https://openalex.org/W842810586","https://openalex.org/W2092919065","https://openalex.org/W4236762297","https://openalex.org/W3138801416","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W2169232658","https://openalex.org/W2444550338"],"abstract_inverted_index":{"A":[0],"major":[1],"obstacle":[2],"to":[3,55,102],"the":[4,13,35,44,57,67,113,116],"development":[5],"of":[6,37,43,59,115],"Natural":[7],"Language":[8],"Processing":[9],"(NLP)":[10],"methods":[11],"in":[12,74,94],"biomedical":[14,77],"domain":[15],"is":[16],"data":[17,27,45,69,73,92,99,118],"accessibility.":[18],"This":[19],"problem":[20],"can":[21,100],"be":[22],"addressed":[23],"by":[24],"generating":[25],"medical":[26],"artificially.":[28],"Most":[29],"previous":[30],"studies":[31],"have":[32],"focused":[33],"on":[34],"generation":[36,58],"short":[38],"clinical":[39,60],"text,":[40],"and":[41,82],"evaluation":[42],"utility":[46],"has":[47],"been":[48],"limited.":[49],"We":[50,65,86,110],"propose":[51],"a":[52],"generic":[53],"methodology":[54],"guide":[56],"text":[61,80],"with":[62,96],"key":[63,76],"phrases.":[64],"use":[66],"artificial":[68],"as":[70],"additional":[71],"training":[72,91,98,127],"two":[75],"NLP":[78,120],"tasks:":[79],"classification":[81],"temporal":[83],"relation":[84],"extraction.":[85],"show":[87],"that":[88],"artificially":[89],"generated":[90,117],"used":[93],"conjunction":[95],"real":[97,126],"lead":[101],"performance":[103],"boosts":[104],"for":[105,119],"datagreedy":[106],"neural":[107],"network":[108],"algorithms.":[109],"also":[111],"demonstrate":[112],"usefulness":[114],"setups":[121],"where":[122],"it":[123],"fully":[124],"replaces":[125],"data.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}