{"id":"https://openalex.org/W2751657485","doi":"https://doi.org/10.1145/3103010.3121044","title":"Learning before Learning","display_name":"Learning before Learning","publication_year":2017,"publication_date":"2017-08-31","ids":{"openalex":"https://openalex.org/W2751657485","doi":"https://doi.org/10.1145/3103010.3121044","mag":"2751657485"},"language":"en","primary_location":{"id":"doi:10.1145/3103010.3121044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"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/A5022519243","display_name":"Steven J. Simske","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Simske","raw_affiliation_strings":["HP, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010432181","display_name":"Marie Vans","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marie Vans","raw_affiliation_strings":["HP, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I4210122178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210122178"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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":0.9950000047683716,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7611347436904907},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7332301139831543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6357913017272949},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6357433795928955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6146278381347656},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.579372763633728},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4770185947418213},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4645960330963135},{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.46410903334617615},{"id":"https://openalex.org/keywords/learning-analytics","display_name":"Learning analytics","score":0.42712274193763733},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4189290404319763},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4102785587310791},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3064749836921692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09493079781532288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611347436904907},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7332301139831543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6357913017272949},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6357433795928955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6146278381347656},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.579372763633728},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4770185947418213},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4645960330963135},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.46410903334617615},{"id":"https://openalex.org/C2777648619","wikidata":"https://www.wikidata.org/wiki/Q2845208","display_name":"Learning analytics","level":2,"score":0.42712274193763733},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4189290404319763},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4102785587310791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3064749836921692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09493079781532288},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3103010.3121044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3103010.3121044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W631245679","https://openalex.org/W1514060118","https://openalex.org/W1721182246","https://openalex.org/W1978394996","https://openalex.org/W1997841190","https://openalex.org/W2003984229","https://openalex.org/W2024932032","https://openalex.org/W2028747520","https://openalex.org/W2043765769","https://openalex.org/W2511006888"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4255621315","https://openalex.org/W3025951784","https://openalex.org/W4317548404","https://openalex.org/W4245382487","https://openalex.org/W2087783760","https://openalex.org/W2489668743","https://openalex.org/W1509924131","https://openalex.org/W2341679435"],"abstract_inverted_index":{"In":[0],"the":[1,7,22,34,39,45,60,79,101,114,118,132,139,162,168,183],"world":[2],"of":[3,9,24,30,50,55,78,86,191,201],"ground":[4],"truthing--that":[5],"is,":[6,129],"collection":[8],"highly":[10],"valuable":[11],"labeled":[12,46,115,119],"training":[13,26,47,135,173],"and":[14,36,53,62,70,134,171,186,195,208],"validation":[15,133,175],"data-there":[16],"is":[17,49,82,145,205],"a":[18,28,84,148],"tendency":[19],"to":[20,99,103,182],"follow":[21],"path":[23],"first":[25],"on":[27],"set":[29],"data,":[31,35],"then":[32,37,178,206],"validating":[33],"testing":[38],"data.":[40],"However,":[41],"in":[42,137],"many":[43],"cases":[44],"data":[48,94,116,120],"non-uniform":[51,56],"quality,":[52],"thus":[54],"value":[57],"for":[58,66,105,124],"assessing":[59],"accuracy":[61],"other":[63],"performance":[64],"indicators":[65],"analytics":[67],"algorithms,":[68],"systems":[69],"processes.":[71],"This":[72,141],"means":[73],"that":[74,109,128,188],"one":[75,110],"or":[76,88,91],"more":[77,89],"so-labeled":[80],"classes":[81,164,194],"likely":[83],"mixture":[85],"two":[87],"clusters":[90],"sub-classes.":[92],"These":[93],"may":[95],"inhibit":[96],"our":[97],"ability":[98],"assess":[100],"classifier":[102],"use":[104],"deployment.":[106],"We":[107,159,177],"argue":[108],"must":[111],"learn":[112],"about":[113],"before":[117,143],"can":[121],"be":[122],"used":[123],"downstream":[125],"machine":[126],"learning;":[127],"we":[130],"reverse":[131],"steps":[136],"building":[138],"classifier.":[140],"\"learning":[142],"learning\"":[144],"assessed":[146],"using":[147,167],"CNN":[149,184],"corpus":[150,185],"(cnn.com)":[151],"which":[152],"was":[153],"hand-labeled":[154],"as":[155],"comprising":[156],"12":[157],"classes.":[158,198],"show":[160,187],"how":[161,172],"suspect":[163],"are":[165],"identified":[166],"initial":[169],"validation,":[170],"after":[174],"occurs.":[176],"apply":[179],"this":[180,202],"process":[181],"it":[189],"consists":[190],"9":[192],"high-quality":[193],"three":[196],"mixed-quality":[197],"The":[199],"effects":[200],"validation-training":[203],"approach":[204],"shown":[207],"discussed.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}