{"id":"https://openalex.org/W3211995690","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.252","title":"Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification","display_name":"Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3211995690","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.252","mag":"3211995690"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.252","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.252","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.252","pdf_url":"https://aclanthology.org/2021.emnlp-main.252.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.252.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035416936","display_name":"Jiachen Tian","orcid":"https://orcid.org/0000-0001-9476-8296","observed_orcids":["https://orcid.org/0000-0001-9476-8296"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachen Tian","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012932387","display_name":"Shizhan Chen","orcid":"https://orcid.org/0000-0002-4430-4765","observed_orcids":["https://orcid.org/0000-0002-4430-4765"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhan Chen","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030524599","display_name":"Xiaowang Zhang","orcid":"https://orcid.org/0000-0002-3931-3886","observed_orcids":["https://orcid.org/0000-0002-3931-3886"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowang Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074214393","display_name":"Zhiyong Feng","orcid":"https://orcid.org/0000-0001-8158-7453","observed_orcids":["https://orcid.org/0000-0001-8158-7453"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Feng","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055232825","display_name":"Deyi Xiong","orcid":"https://orcid.org/0000-0002-2353-5038","observed_orcids":["https://orcid.org/0000-0002-2353-5038","https://orcid.org/0009-0007-6501-4496"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Xiong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021162098","display_name":"Shaojuan Wu","orcid":"https://orcid.org/0000-0002-7407-485X","observed_orcids":["https://orcid.org/0000-0002-7407-485X"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojuan Wu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043701657","display_name":"Chunliu Dou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunliu Dou","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.1526,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8201777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3148","last_page":"3161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9312000274658203,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9312000274658203,"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":0.04800000041723251,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.004100000020116568,"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/imbalanced-text-classification","display_name":"imbalanced text classification","score":0.9980000257492065},{"id":"https://openalex.org/keywords/minority-class","display_name":"minority class","score":0.7289999723434448},{"id":"https://openalex.org/keywords/re-embedding","display_name":"re-embedding","score":0.9259999990463257},{"id":"https://openalex.org/keywords/mutual-information-loss","display_name":"mutual information loss","score":0.7419999837875366},{"id":"https://openalex.org/keywords/disentangled-representations","display_name":"disentangled representations","score":0.8029999732971191},{"id":"https://openalex.org/keywords/multi-head-attention","display_name":"multi-head attention","score":0.8379999995231628},{"id":"https://openalex.org/keywords/semantic-fusion","display_name":"semantic fusion","score":0.6299999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848852872848511},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7304248809814453},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6597824096679688},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6414087414741516},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6189374327659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987920761108398},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.584553062915802},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5560125708580017},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5119927525520325},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4404413104057312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40703529119491577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34439629316329956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3337421417236328},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33196496963500977},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.252","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.252","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.252","pdf_url":"https://aclanthology.org/2021.emnlp-main.252.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.252","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.252","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.252","pdf_url":"https://aclanthology.org/2021.emnlp-main.252.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1269876823","display_name":null,"funder_award_id":"61972455","funder_id":"https://openalex.org/F4320322701","funder_display_name":"Tianjin University"},{"id":"https://openalex.org/G2481330354","display_name":null,"funder_award_id":"2019XRX-0032","funder_id":"https://openalex.org/F4320322701","funder_display_name":"Tianjin University"},{"id":"https://openalex.org/G4304333080","display_name":null,"funder_award_id":"61972455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G960922202","display_name":null,"funder_award_id":"2019XRX-0032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322701","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211995690.pdf","grobid_xml":"https://content.openalex.org/works/W3211995690.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1832693441","https://openalex.org/W2057988282","https://openalex.org/W2094705469","https://openalex.org/W2102605133","https://openalex.org/W2104933073","https://openalex.org/W2118978333","https://openalex.org/W2132791018","https://openalex.org/W2136144249","https://openalex.org/W2148143831","https://openalex.org/W2168356304","https://openalex.org/W2407776548","https://openalex.org/W2567149662","https://openalex.org/W2607037079","https://openalex.org/W2803832867","https://openalex.org/W2884561390","https://openalex.org/W2897069058","https://openalex.org/W2897299086","https://openalex.org/W2903718012","https://openalex.org/W2904945528","https://openalex.org/W2905236149","https://openalex.org/W2908747729","https://openalex.org/W2911209675","https://openalex.org/W2950813464","https://openalex.org/W2952120674","https://openalex.org/W2962721361","https://openalex.org/W2963248348","https://openalex.org/W2963351448","https://openalex.org/W2963667126","https://openalex.org/W2964008635","https://openalex.org/W2972231924","https://openalex.org/W2981188200","https://openalex.org/W3034328552","https://openalex.org/W3035542229","https://openalex.org/W3048025970","https://openalex.org/W3048804322","https://openalex.org/W3091940082","https://openalex.org/W3094280243","https://openalex.org/W3098199128","https://openalex.org/W3102124851","https://openalex.org/W3123939835","https://openalex.org/W4243367342"],"related_works":["https://openalex.org/W4320854298","https://openalex.org/W4416710899","https://openalex.org/W7095751541","https://openalex.org/W2979624122","https://openalex.org/W7166853698","https://openalex.org/W7170053860","https://openalex.org/W6910754138","https://openalex.org/W3189792414","https://openalex.org/W2471991522","https://openalex.org/W4409785640"],"abstract_inverted_index":{"Difficult":[0],"samples":[1,78],"of":[2,55,64,98,105,146],"the":[3,26,48,52,102,106,125],"minority":[4,107,126],"class":[5],"in":[6,101],"imbalanced":[7,147],"text":[8,148],"classification":[9,149],"are":[10,18],"usually":[11],"hard":[12],"to":[13,46,94,120,135],"be":[14],"classified":[15],"as":[16],"they":[17],"embedded":[19],"into":[20],"an":[21,80],"overlapping":[22],"semantic":[23,67,118,133],"region":[24,104],"with":[25,79,124],"majority":[27,77],"class.In":[28],"this":[29],"paper,":[30],"we":[31],"propose":[32],"a":[33,56,66,86,111,144],"Mutual":[34],"Information":[35],"constrained":[36],"Semantically":[37],"Oversampling":[38],"framework":[39],"(MISO)":[40],"that":[41,70,90,115,152],"can":[42],"generate":[43,136],"anchor":[44,137,153],"instances":[45,138,154],"help":[47,155],"backbone":[49],"network":[50],"determine":[51],"re-embedding":[53],"position":[54],"non-overlapping":[57,103],"representation":[58],"for":[59,139],"each":[60,140],"difficult":[61,75,141],"sample.MISO":[62],"consists":[63],"(1)":[65],"fusion":[68],"module":[69],"learns":[71],"entangled":[72,99],"semantics":[73,100],"among":[74],"and":[76,109,128],"adaptive":[81],"multi-head":[82],"attention":[83],"mechanism,":[84],"(2)":[85],"mutual":[87],"information":[88],"loss":[89],"forces":[91],"our":[92],"model":[93],"learn":[95],"new":[96],"representations":[97,119,134],"class,":[108,127],"(3)":[110],"coupled":[112],"adversarial":[113],"encoder-decoder":[114],"fine-tunes":[116],"disentangled":[117,132],"remain":[121],"their":[122],"correlations":[123],"then":[129],"using":[130],"these":[131],"sample.Experiments":[142],"on":[143],"variety":[145],"tasks":[150],"demonstrate":[151],"classifiers":[156],"achieve":[157],"significant":[158],"improvements":[159],"over":[160],"strong":[161],"baselines.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-11-22T00:00:00"}