{"id":"https://openalex.org/W2165086927","doi":"https://doi.org/10.1145/1597735.1597754","title":"Reducing class imbalance during active learning for named entity annotation","display_name":"Reducing class imbalance during active learning for named entity annotation","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2165086927","doi":"https://doi.org/10.1145/1597735.1597754","mag":"2165086927"},"language":"en","primary_location":{"id":"doi:10.1145/1597735.1597754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1597735.1597754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international conference on Knowledge capture","raw_type":"proceedings-article"},"type":"article","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/A5002347902","display_name":"Katrin Tomanek","orcid":"https://orcid.org/0000-0002-9873-7144"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Katrin Tomanek","raw_affiliation_strings":["Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044841280","display_name":"Udo Hahn","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Udo Hahn","raw_affiliation_strings":["Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002347902"],"corresponding_institution_ids":["https://openalex.org/I76198965"],"apc_list":null,"apc_paid":null,"fwci":4.5051,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.94807651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9907000064849854,"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/T10028","display_name":"Topic Modeling","score":0.9847000241279602,"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":0.8011091947555542},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.7144262790679932},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7035580277442932},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5976973176002502},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5903599858283997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868419408798218},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5748120546340942},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5482122302055359},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.464793860912323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4151926636695862},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08009001612663269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011091947555542},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7144262790679932},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7035580277442932},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5976973176002502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5903599858283997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868419408798218},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5748120546340942},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5482122302055359},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.464793860912323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4151926636695862},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08009001612663269},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1597735.1597754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1597735.1597754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.458.3488","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.458.3488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://julielab.de/coling_multimedia/de/downloads/Papers/kcap2009_al_class_imbalance_with_acm_copyright.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W167016754","https://openalex.org/W173861811","https://openalex.org/W199218251","https://openalex.org/W239119325","https://openalex.org/W1528361845","https://openalex.org/W1941659294","https://openalex.org/W1976721183","https://openalex.org/W1998259579","https://openalex.org/W2010588484","https://openalex.org/W2074064986","https://openalex.org/W2085989833","https://openalex.org/W2096175520","https://openalex.org/W2099550922","https://openalex.org/W2116159459","https://openalex.org/W2147880316","https://openalex.org/W2148143831","https://openalex.org/W2154250549","https://openalex.org/W2166496241","https://openalex.org/W2570764145"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2030816003","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W4239992647","https://openalex.org/W2076325756","https://openalex.org/W81423522"],"abstract_inverted_index":{"In":[0],"lots":[1],"of":[2,52,88,106,119],"natural":[3],"language":[4],"processing":[5],"tasks,":[6],"the":[7,18,50,86,104],"classes":[8,110],"to":[9,30,43,59,77],"be":[10],"dealt":[11],"with":[12],"often":[13],"occur":[14],"heavily":[15],"imbalanced":[16],"in":[17,85,117],"underlying":[19],"data":[20,28,63],"set":[21],"and":[22,39,102],"classifiers":[23,107],"trained":[24],"on":[25,108],"such":[26],"skewed":[27],"tend":[29],"exhibit":[31],"poor":[32],"performance":[33,105,116],"for":[34],"low-frequency":[35],"classes.":[36],"We":[37,81],"introduce":[38],"compare":[40],"different":[41],"approaches":[42],"reduce":[44,99],"class":[45,100],"imbalance":[46,101],"by":[47],"design":[48],"within":[49],"context":[51,87],"active":[53],"learning":[54],"(AL).":[55],"Our":[56,92],"goal":[57],"is":[58,72],"compile":[60],"more":[61],"balanced":[62],"sets":[64],"up":[65],"front":[66],"during":[67],"annotation":[68],"time":[69],"when":[70],"AL":[71],"used":[73],"as":[74],"a":[75,113],"strategy":[76],"acquire":[78],"training":[79],"material.":[80],"situate":[82],"our":[83],"approach":[84],"named":[89],"entity":[90],"recognition.":[91],"experiments":[93],"reveal":[94],"that":[95],"we":[96],"can":[97],"indeed":[98],"increase":[103],"minority":[109],"while":[111],"preserving":[112],"good":[114],"overall":[115],"terms":[118],"macro":[120],"F-score.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}