{"id":"https://openalex.org/W2963908732","doi":"https://doi.org/10.18653/v1/w18-6114","title":"Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data","display_name":"Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963908732","doi":"https://doi.org/10.18653/v1/w18-6114","mag":"2963908732"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6114","pdf_url":"https://www.aclweb.org/anthology/W18-6114.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6114.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078647228","display_name":"R. Andrew Kreek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099208","display_name":"Allstate (United States)","ror":"https://ror.org/00z58wj40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099208"]},{"id":"https://openalex.org/I4210130169","display_name":"Ameriprise Financial (United States)","ror":"https://ror.org/04bcw2e70","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130169"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Andrew Kreek","raw_affiliation_strings":["Allstate Insurance Company Seattle, WA USA"],"affiliations":[{"raw_affiliation_string":"Allstate Insurance Company Seattle, WA USA","institution_ids":["https://openalex.org/I4210130169","https://openalex.org/I4210099208"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046655683","display_name":"Emilia Apostolova","orcid":"https://orcid.org/0000-0003-2081-4530"},"institutions":[{"id":"https://openalex.org/I4210098728","display_name":"Language Computer (United States)","ror":"https://ror.org/013mgh495","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098728"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Emilia Apostolova","raw_affiliation_strings":["Language.ai Chicago, IL USA"],"affiliations":[{"raw_affiliation_string":"Language.ai Chicago, IL USA","institution_ids":["https://openalex.org/I4210098728"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046655683"],"corresponding_institution_ids":["https://openalex.org/I4210098728"],"apc_list":null,"apc_paid":null,"fwci":0.6756,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79078839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9972000122070312,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9972000122070312,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9836999773979187,"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":0.9818000197410583,"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":0.7522056102752686},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6153271198272705},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5069068074226379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46404215693473816},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4487416744232178},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3384673595428467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3383324146270752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522056102752686},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6153271198272705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5069068074226379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46404215693473816},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4487416744232178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3384673595428467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3383324146270752},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.18653/v1/w18-6114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6114","pdf_url":"https://www.aclweb.org/anthology/W18-6114.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6114","pdf_url":"https://www.aclweb.org/anthology/W18-6114.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963908732.pdf","grobid_xml":"https://content.openalex.org/works/W2963908732.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W877541198","https://openalex.org/W1832693441","https://openalex.org/W2005178237","https://openalex.org/W2039013656","https://openalex.org/W2069172670","https://openalex.org/W2092911974","https://openalex.org/W2099140003","https://openalex.org/W2116405309","https://openalex.org/W2133058591","https://openalex.org/W2157023969","https://openalex.org/W2158899491","https://openalex.org/W2167460663","https://openalex.org/W2184928272","https://openalex.org/W2618574054","https://openalex.org/W2768768198","https://openalex.org/W2952230511","https://openalex.org/W2962735169","https://openalex.org/W2963626623","https://openalex.org/W3120740533","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W2551249631","https://openalex.org/W160673860","https://openalex.org/W2963642612","https://openalex.org/W4289548080","https://openalex.org/W1585680390","https://openalex.org/W3173587717","https://openalex.org/W2113005879","https://openalex.org/W3165456129","https://openalex.org/W2070517798","https://openalex.org/W4312793562"],"abstract_inverted_index":{"Industry":[0],"datasets":[1,80],"used":[2,81],"for":[3,9,86],"text":[4],"classification":[5],"are":[6,20],"rarely":[7],"created":[8],"that":[10],"purpose.":[11],"In":[12,44],"most":[13],"cases,":[14],"the":[15,34,41,49,62,65,75],"data":[16,60],"and":[17],"target":[18],"predictions":[19],"a":[21],"byproduct":[22],"of":[23,51,77],"accumulated":[24],"historical":[25,59],"data,":[26],"typically":[27],"fraught":[28],"with":[29],"noise,":[30],"present":[31],"in":[32,40],"both":[33],"text-based":[35],"document,":[36],"as":[37,39],"well":[38,53],"targeted":[42],"labels.":[43],"this":[45],"work,":[46],"we":[47],"address":[48],"question":[50],"how":[52],"performance":[54,63],"metrics":[55],"computed":[56],"on":[57,64],"noisy,":[58],"reflect":[61],"intended":[66],"future":[67],"machine":[68],"learning":[69],"model":[70],"input.":[71],"The":[72],"results":[73],"demonstrate":[74],"utility":[76],"dirty":[78],"training":[79],"to":[82],"build":[83],"prediction":[84,90],"models":[85],"cleaner":[87],"(and":[88],"different)":[89],"inputs.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}