{"id":"https://openalex.org/W2026257418","doi":"https://doi.org/10.1145/1089815.1089818","title":"Instance Filtering for entity recognition","display_name":"Instance Filtering for entity recognition","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W2026257418","doi":"https://doi.org/10.1145/1089815.1089818","mag":"2026257418"},"language":"en","primary_location":{"id":"doi:10.1145/1089815.1089818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089818","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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/A5087419620","display_name":"Alfio Gliozzo","orcid":"https://orcid.org/0000-0002-8044-2911"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alfio Massimiliano Gliozzo","raw_affiliation_strings":["ITC-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"ITC-irst, Trento, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062913763","display_name":"Claudio Giuliano","orcid":"https://orcid.org/0000-0002-2329-6372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudio Giuliano","raw_affiliation_strings":["ITC-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"ITC-irst, Trento, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049898867","display_name":"Raffaella Rinaldi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raffaella Rinaldi","raw_affiliation_strings":["ITC-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"ITC-irst, Trento, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087419620"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3163,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8395667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":"1","first_page":"11","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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":0.9983000159263611,"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":0.8933476805686951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6522338390350342},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6377869844436646},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6081289052963257},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5450754761695862},{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.4829256236553192},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4812321662902832},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4596220552921295},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.457236111164093},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4495576024055481},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4228239357471466},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37181487679481506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8933476805686951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6522338390350342},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6377869844436646},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6081289052963257},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5450754761695862},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.4829256236553192},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4812321662902832},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4596220552921295},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.457236111164093},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4495576024055481},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4228239357471466},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37181487679481506},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1089815.1089818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089818","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W200042785","https://openalex.org/W1566173369","https://openalex.org/W1965895350","https://openalex.org/W1973702599","https://openalex.org/W2021331223","https://openalex.org/W2023450550","https://openalex.org/W2047782770","https://openalex.org/W2053724458","https://openalex.org/W2115563868","https://openalex.org/W2119821739","https://openalex.org/W2122496402","https://openalex.org/W2127031049","https://openalex.org/W2147079026","https://openalex.org/W2149430911","https://openalex.org/W2155925463","https://openalex.org/W2163107094","https://openalex.org/W2163194396","https://openalex.org/W2435251607","https://openalex.org/W2938524560","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2189529952","https://openalex.org/W3122032734","https://openalex.org/W28389960","https://openalex.org/W3144675622","https://openalex.org/W3124374489","https://openalex.org/W4390063540","https://openalex.org/W3080076373","https://openalex.org/W2549038846","https://openalex.org/W2463389856","https://openalex.org/W3028958383"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,142],"propose":[4],"Instance":[5,21,85],"Filtering":[6,22,86],"as":[7,44,46],"preprocessing":[8],"step":[9],"for":[10,15,152],"supervised":[11],"classification-based":[12],"learning":[13,65],"systems":[14],"entity":[16,113],"recognition.":[17],"The":[18],"goal":[19],"of":[20,62,84,103,147],"is":[23,50],"to":[24,100],"reduce":[25],"both":[26,53,130],"the":[27,32,54,60,64,73,97,131,134,148,161],"skewed":[28],"class":[29,83],"distribution":[30],"and":[31,56,66,120,126,133,154],"data":[33,135],"set":[34,136],"size":[35,137],"by":[36],"eliminating":[37],"negative":[38],"instances,":[39],"while":[40,69,156],"preserving":[41],"positive":[42],"ones":[43],"much":[45],"possible.":[47],"This":[48],"process":[49],"performed":[51,77],"on":[52,81,110],"training":[55,153],"test":[57],"set,":[58],"with":[59],"effect":[61],"reducing":[63],"classification":[67],"time,":[68],"maintaining":[70,157],"or":[71],"improving":[72],"prediction":[74,162],"accuracy.":[75,163],"We":[76,106],"a":[78,82,101],"comparative":[79],"study":[80],"techniques,":[87],"called":[88],"Stop":[89],"Word":[90],"Filters":[91],",":[92],"that":[93,129],"simply":[94],"remove":[95],"all":[96],"tokens":[98],"belonging":[99],"list":[102],"stop":[104],"words.":[105],"evaluated":[107],"our":[108],"approach":[109],"three":[111],"different":[112],"recognition":[114],"tasks":[115],"(i.e.":[116],"Named":[117],"Entity,":[118],"Bio-Entity":[119],"Temporal":[121],"Expression":[122],"Recognition)":[123],"in":[124],"English":[125],"Dutch,":[127],"showing":[128],"skewness":[132],"are":[138],"drastically":[139],"reduced.":[140],"Consequently,":[141],"reported":[143],"an":[144],"impressive":[145],"reduction":[146],"computation":[149],"time":[150],"required":[151],"classification,":[155],"(and":[158],"sometimes":[159],"improving)":[160]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}