{"id":"https://openalex.org/W4231064004","doi":"https://doi.org/10.1145/860500.860546","title":"Optimizing term vectors for efficient and robust filtering","display_name":"Optimizing term vectors for efficient and robust filtering","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W4231064004","doi":"https://doi.org/10.1145/860500.860546"},"language":"en","primary_location":{"id":"doi:10.1145/860500.860546","doi":"https://doi.org/10.1145/860500.860546","is_oa":false,"landing_page_url":"https://doi.org/10.1145/860500.860546","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":"Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval - SIGIR '03","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/A5025362921","display_name":"David Andreoff Evans","orcid":"https://orcid.org/0000-0003-4059-4416","observed_orcids":["https://orcid.org/0000-0003-4059-4416"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David A. Evans","raw_affiliation_strings":["Clairvoyance Corporation, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clairvoyance Corporation, Pittsburgh, PA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jeffrey Bennett","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey Bennett","raw_affiliation_strings":["Clairvoyance Corporation, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clairvoyance Corporation, Pittsburgh, PA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111755962","display_name":"David A. Hull","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David A. Hull","raw_affiliation_strings":["Clairvoyance Corporation, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clairvoyance Corporation, Pittsburgh, PA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33710954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9419000148773193,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9419000148773193,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.03200000151991844,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.010499999858438969,"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/term-selection","display_name":"term selection","score":0.8849999904632568},{"id":"https://openalex.org/keywords/term-vectors","display_name":"term vectors","score":0.593999981880188},{"id":"https://openalex.org/keywords/document-filtering","display_name":"document filtering","score":0.6230000257492065},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7569499015808105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396636009216309},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6583417654037476},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.63640958070755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5338320136070251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5261111855506897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227087736129761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.516628086566925},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4714423418045044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4595325291156769},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4102631211280823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3565976321697235},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08087286353111267},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/860500.860546","doi":"https://doi.org/10.1145/860500.860546","is_oa":false,"landing_page_url":"https://doi.org/10.1145/860500.860546","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":"Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval - SIGIR '03","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1649417344","https://openalex.org/W2084044465","https://openalex.org/W119363577","https://openalex.org/W1501167212","https://openalex.org/W2014165675","https://openalex.org/W2984049620","https://openalex.org/W2392501019","https://openalex.org/W4242445188","https://openalex.org/W1024444168","https://openalex.org/W2096349503"],"abstract_inverted_index":{"We":[0],"describe":[1],"an":[2],"efficient,":[3],"robust":[4],"method":[5],"for":[6,11,53,82],"selecting":[7],"and":[8,45,73,100,106],"optimizing":[9],"terms":[10],"a":[12,36,43],"classification":[13],"or":[14],"filtering":[15],"task.":[16],"Terms":[17],"are":[18],"extracted":[19],"from":[20],"positive":[21],"examples":[22],"in":[23,79,112],"training":[24,66],"data":[25],"based":[26],"on":[27,90],"several":[28],"alternative":[29],"term-selection":[30],"algorithms,":[31],"then":[32],"combined":[33],"additively":[34],"after":[35],"simple":[37],"term-score":[38],"normalization":[39],"step":[40],"to":[41],"produce":[42],"merged":[44],"ranked":[46],"master":[47,55],"term":[48],"vector.":[49],"The":[50,68],"score":[51],"threshold":[52],"the":[54,64],"vector":[56],"is":[57],"set":[58],"via":[59],"beta-gamma":[60],"regulation":[61],"over":[62,97],"all":[63],"available":[65],"data.":[67],"process":[69],"avoids":[70],"para-meter":[71],"calibrations":[72],"protracted":[74],"training.":[75],"It":[76],"also":[77],"results":[78,99,105],"compact":[80],"profiles":[81],"run-time":[83],"evaluation":[84],"of":[85],"test":[86],"(new)":[87],"documents.":[88],"Results":[89],"TREC-2002":[91],"filtering-task":[92],"datasets":[93],"demonstrate":[94],"substantial":[95],"improvements":[96],"TREC-median":[98],"rival":[101],"both":[102],"idealized":[103],"IR-based":[104],"optimized":[107],"(and":[108],"expensive)":[109],"SVM-based":[110],"classifiers":[111],"general":[113],"effectiveness.":[114]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2022-05-11T00:00:00"}