{"id":"https://openalex.org/W3010805814","doi":"https://doi.org/10.1109/escience.2019.00021","title":"Active Learning Yields Better Training Data for Scientific Named Entity Recognition","display_name":"Active Learning Yields Better Training Data for Scientific Named Entity Recognition","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W3010805814","doi":"https://doi.org/10.1109/escience.2019.00021","mag":"3010805814"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2019.00021","doi":"https://doi.org/10.1109/escience.2019.00021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2019.00021","pdf_url":null,"source":{"id":"https://openalex.org/S4306419448","display_name":"International Conference on e-Science","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Conference on eScience (eScience)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5080703148","display_name":"Roselyne Tchoua","orcid":"https://orcid.org/0000-0002-7195-4456","observed_orcids":["https://orcid.org/0000-0002-7195-4456"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roselyne Tchoua","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008568853","display_name":"Aswathy Ajith","orcid":"https://orcid.org/0000-0001-7812-2962","observed_orcids":["https://orcid.org/0000-0001-7812-2962"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswathy Ajith","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033423239","display_name":"Zhi Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Hong","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021403239","display_name":"Logan T. Ward","orcid":"https://orcid.org/0000-0002-1323-5939","observed_orcids":["https://orcid.org/0000-0002-1323-5939"]},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Logan Ward","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805","observed_orcids":["https://orcid.org/0000-0002-7370-4805"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005951766","display_name":"Debra J. Audus","orcid":"https://orcid.org/0000-0002-5937-7721","observed_orcids":["https://orcid.org/0000-0002-5937-7721"]},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debra Audus","raw_affiliation_strings":["National Institute of Standards and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003276517","display_name":"Shrayesh N. Patel","orcid":"https://orcid.org/0000-0003-3657-827X","observed_orcids":["https://orcid.org/0000-0003-3657-827X"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrayesh Patel","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068853530","display_name":"Juan Pablo","orcid":"https://orcid.org/0000-0002-3526-516X","observed_orcids":["https://orcid.org/0000-0002-3526-516X"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan de Pablo","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian T Foster","orcid":"https://orcid.org/0000-0003-2129-5269","observed_orcids":["https://orcid.org/0000-0003-2129-5269"]},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0521,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83235301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.47049999237060547,"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":0.47049999237060547,"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":0.396699994802475,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.03370000049471855,"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/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9810000061988831},{"id":"https://openalex.org/keywords/expert-annotation","display_name":"expert annotation","score":0.6340000033378601},{"id":"https://openalex.org/keywords/training-data-generation","display_name":"training data generation","score":0.621999979019165},{"id":"https://openalex.org/keywords/synonymy-linguistics","display_name":"synonymy (linguistics)","score":0.6539999842643738},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475855350494385},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6975921988487244},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6067521572113037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621210932731628},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5487003922462463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4360206723213196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4269864559173584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3690432608127594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3430154323577881},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10084497928619385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience.2019.00021","doi":"https://doi.org/10.1109/escience.2019.00021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2019.00021","pdf_url":null,"source":{"id":"https://openalex.org/S4306419448","display_name":"International Conference on e-Science","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 15th International Conference on eScience (eScience)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, justice, and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W168564468","https://openalex.org/W1483816357","https://openalex.org/W1489949474","https://openalex.org/W1513874326","https://openalex.org/W1614298861","https://openalex.org/W1845402413","https://openalex.org/W1978633512","https://openalex.org/W1998523535","https://openalex.org/W2001818158","https://openalex.org/W2029515855","https://openalex.org/W2042932437","https://openalex.org/W2047782770","https://openalex.org/W2052569640","https://openalex.org/W2080021732","https://openalex.org/W2094728533","https://openalex.org/W2101234009","https://openalex.org/W2101553882","https://openalex.org/W2103931177","https://openalex.org/W2107005506","https://openalex.org/W2111044246","https://openalex.org/W2127031049","https://openalex.org/W2136504847","https://openalex.org/W2141708418","https://openalex.org/W2144578941","https://openalex.org/W2145870108","https://openalex.org/W2150252713","https://openalex.org/W2153579005","https://openalex.org/W2153839362","https://openalex.org/W2162233306","https://openalex.org/W2165671627","https://openalex.org/W2169491861","https://openalex.org/W2252147815","https://openalex.org/W2291908932","https://openalex.org/W2404161646","https://openalex.org/W2466758040","https://openalex.org/W2468328197","https://openalex.org/W2472949835","https://openalex.org/W2493916176","https://openalex.org/W2508342052","https://openalex.org/W2523785361","https://openalex.org/W2746791238","https://openalex.org/W2754122850","https://openalex.org/W2765386496","https://openalex.org/W2769151956","https://openalex.org/W2900873656","https://openalex.org/W2903158431","https://openalex.org/W2903477886","https://openalex.org/W2950659199","https://openalex.org/W4313371817"],"related_works":["https://openalex.org/W2950659199","https://openalex.org/W3111995236","https://openalex.org/W7202209407","https://openalex.org/W4310609307","https://openalex.org/W7131891132","https://openalex.org/W4406611865","https://openalex.org/W4415257103","https://openalex.org/W3088896851","https://openalex.org/W3092570611","https://openalex.org/W2052643363"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress":[2],"in":[3,18,43,114],"natural":[4],"language":[5],"processing,":[6],"machine":[7],"learning":[8,156],"models":[9,120],"require":[10],"substantial":[11],"expertannotated":[12],"training":[13,89],"data":[14,135],"to":[15,70,81,87,96,121,136,157,176,181],"perform":[16],"well":[17],"tasks":[19],"such":[20],"as":[21,91],"named":[22],"entity":[23,27],"recognition":[24],"(NER)":[25],"and":[26,66,129,150,164],"relations":[28],"extraction.":[29],"Furthermore,":[30],"NER":[31,187],"is":[32,147],"often":[33],"more":[34,160],"complicated":[35],"when":[36],"working":[37],"with":[38,72],"scientific":[39,112],"text.":[40,115],"For":[41],"example,":[42],"polymer":[44,82],"science,":[45,83],"chemical":[46,186],"structure":[47],"may":[48,68],"be":[49,59],"encoded":[50],"using":[51,61],"nonstandard":[52],"naming":[53],"conventions,":[54],"the":[55,132],"same":[56],"concept":[57],"can":[58],"expressed":[60],"many":[62],"different":[63],"terms":[64],"(synonymy),":[65],"authors":[67],"refer":[69],"polymers":[71],"ad-hoc":[73],"labels.":[74],"These":[75],"challenges,":[76],"which":[77],"are":[78,94],"not":[79],"unique":[80],"make":[84],"it":[85],"difficult":[86],"generate":[88,122],"data,":[90],"specialized":[92],"skills":[93],"needed":[95],"label":[97],"text":[98],"correctly.":[99],"We":[100],"have":[101],"previously":[102],"designed":[103],"polyNER,":[104],"a":[105,138,143,184],"semi-automated":[106],"system":[107],"for":[108,125],"efficient":[109],"identification":[110],"of":[111,173,183],"entities":[113],"PolyNER":[116,141],"applies":[117],"word":[118],"embedding":[119],"entity-rich":[123],"corpora":[124],"productive":[126],"expert":[127,174],"labeling,":[128],"then":[130],"uses":[131],"resulting":[133],"labeled":[134],"bootstrap":[137],"context-based":[139],"classifier.":[140],"facilitates":[142],"labeling":[144],"process":[145],"that":[146,182],"otherwise":[148],"tedious":[149],"expensive.":[151],"Here,":[152],"we":[153],"use":[154],"active":[155],"efficiently":[158],"obtain":[159],"annotations":[161],"from":[162],"experts":[163],"improve":[165],"performance.":[166],"Our":[167],"approach":[168],"requires":[169],"just":[170],"five":[171],"hours":[172],"time":[175],"achieve":[177],"discrimination":[178],"capacity":[179],"comparable":[180],"state-of-the-art":[185],"toolkit.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-03-23T00:00:00"}