{"id":"https://openalex.org/W3208432929","doi":"https://doi.org/10.1145/3459637.3482077","title":"Counterfactual Generative Smoothing for Imbalanced Natural Language Classification","display_name":"Counterfactual Generative Smoothing for Imbalanced Natural Language Classification","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208432929","doi":"https://doi.org/10.1145/3459637.3482077","mag":"3208432929"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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/A5087634233","display_name":"Hojae Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hojae Han","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103182620","display_name":"Seungtaek Choi","orcid":"https://orcid.org/0000-0003-3570-0907"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungtaek Choi","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007729698","display_name":"Myeongho Jeong","orcid":"https://orcid.org/0000-0001-5903-4553"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeongho Jeong","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086882482","display_name":"Jin-woo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin-woo Park","raw_affiliation_strings":["Facebook Inc., Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024873601","display_name":"Seung-won Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-won Hwang","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087634233"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.4197,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70276923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3058","last_page":"3062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9959999918937683,"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":0.9922000169754028,"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/smoothing","display_name":"Smoothing","score":0.8115503787994385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6389774084091187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6187583804130554},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6124011278152466},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5455611944198608},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5070159435272217},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5045615434646606},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.458710253238678},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4323650598526001},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41153624653816223},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35679611563682556},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09840142726898193},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06993326544761658},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0665571391582489}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.8115503787994385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6389774084091187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187583804130554},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6124011278152466},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5455611944198608},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5070159435272217},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5045615434646606},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.458710253238678},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4323650598526001},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41153624653816223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35679611563682556},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09840142726898193},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06993326544761658},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0665571391582489},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/184199","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/184199","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2070246124","https://openalex.org/W2077302143","https://openalex.org/W2136903812","https://openalex.org/W2148143831","https://openalex.org/W2440599146","https://openalex.org/W2753300133","https://openalex.org/W2803609229","https://openalex.org/W2889201969","https://openalex.org/W2905266130","https://openalex.org/W2952120674","https://openalex.org/W2963351448","https://openalex.org/W2970820898","https://openalex.org/W2998184481","https://openalex.org/W3014222654","https://openalex.org/W3034711780","https://openalex.org/W3035542229","https://openalex.org/W3091972074","https://openalex.org/W3104169042","https://openalex.org/W4288107856","https://openalex.org/W4289564002"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3028847759","https://openalex.org/W2393688264","https://openalex.org/W4390143830"],"abstract_inverted_index":{"Classification":[0],"datasets":[1],"are":[2],"often":[3],"biased":[4],"in":[5,67],"observations,":[6,51],"leaving":[7],"onlya":[8],"few":[9],"observations":[10],"for":[11],"minority":[12,50],"classes.":[13],"Our":[14,44,61],"key":[15],"contribution":[16,46],"is":[17],"de-tecting":[18],"and":[19,23,42,49,57,70],"reducing":[20],"Under-represented":[21],"(U-)":[22],"Over-represented(O-)":[24],"artifacts":[25],"from":[26],"dataset":[27],"imbalance,":[28],"by":[29,52],"proposing":[30],"a":[31,54],"Counterfac-tual":[32],"Generative":[33],"Smoothing":[34],"approach":[35],"on":[36],"both":[37,68,75],"feature-space":[38],"anddata-space,":[39],"namely":[40],"CGS_f":[41],"CGS_d.":[43],"technical":[45],"issmoothing":[47],"majority":[48],"sampling":[53],"ma-jority":[55],"seed":[56],"transferring":[58],"to":[59],"minority.":[60],"proposed":[62],"approachesnot":[63],"only":[64],"outperform":[65],"state-of-the-arts":[66],"synthetic":[69],"real-lifedatasets,":[71],"they":[72],"effectively":[73],"reduce":[74],"artifact":[76],"types.":[77]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}