{"id":"https://openalex.org/W7126397443","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.68","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","display_name":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126397443","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.68"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.68","pdf_url":"https://aclanthology.org/2024.findings-eacl.68.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.68.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092029590","display_name":"Oscar Chew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oscar Chew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124686923","display_name":"Hsuan-Tien Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsuan-Tien Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kai-Wei Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124631521","display_name":"Kuan-Hao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuan-Hao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57251444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1013","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.7228999733924866,"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":0.7228999733924866,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.07329999655485153,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.03519999980926514,"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/spurious-relationship","display_name":"Spurious relationship","score":0.6284999847412109},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32260000705718994},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31349998712539673},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.27639999985694885},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2621000111103058}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5289000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28619998693466187},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.68","pdf_url":"https://aclanthology.org/2024.findings-eacl.68.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.68","pdf_url":"https://aclanthology.org/2024.findings-eacl.68.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126397443.pdf","grobid_xml":"https://content.openalex.org/works/W7126397443.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"revealed":[3],"the":[4,17,36,52,65,90],"tendency":[5],"of":[6,67,113],"machine":[7],"learning":[8],"models":[9],"to":[10,85,99,118],"leverage":[11],"spurious":[12,49,68,80,101,120],"correlations":[13,50,69,81,121],"that":[14,35,126],"exist":[15],"in":[16,25,89,122],"training":[18],"set":[19],"but":[20],"may":[21,32],"not":[22],"hold":[23],"true":[24],"general":[26],"circumstances.For":[27],"instance,":[28],"a":[29,71,97,111],"sentiment":[30],"classifier":[31,135],"erroneously":[33,86],"learn":[34],"token":[37],"PERFORMANCES":[38],"is":[39],"commonly":[40],"associated":[41],"with":[42],"positive":[43],"movie":[44],"reviews.Undue":[45],"reliance":[46],"on":[47,58],"such":[48],"degrades":[51],"classifier's":[53],"performance":[54],"when":[55],"it":[56],"deploys":[57],"out-of-distribution":[59],"data.In":[60],"this":[61,93],"paper,":[62],"we":[63,95],"examine":[64],"implications":[66],"through":[70],"novel":[72],"perspective":[73],"called":[74],"neighborhood":[75],"analysis,":[76,94],"which":[77,117],"shows":[78],"how":[79],"lead":[82],"unrelated":[83],"words":[84],"cluster":[87],"together":[88],"embedding":[91],"space.Given":[92],"design":[96],"metric":[98],"detect":[100],"tokens":[102],"and":[103,132],"also":[104],"propose":[105],"NFL":[106,127],"(doN't":[107],"Forget":[108],"your":[109],"Language),":[110],"family":[112],"regularization":[114],"methods":[115],"by":[116],"mitigate":[119],"text":[123],"classification.Experiments":[124],"show":[125],"effectively":[128],"prevents":[129],"erroneous":[130],"clusters":[131],"significantly":[133],"improves":[134],"robustness":[136],"without":[137],"auxiliary":[138],"data.":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}