{"id":"https://openalex.org/W4306317280","doi":"https://doi.org/10.1145/3511808.3557673","title":"Probing the Robustness of Pre-trained Language Models for Entity Matching","display_name":"Probing the Robustness of Pre-trained Language Models for Entity Matching","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317280","doi":"https://doi.org/10.1145/3511808.3557673"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557673","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557673","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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/A5076112778","display_name":"Mehdi Akbarian Rastaghi","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mehdi Akbarian Rastaghi","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043026875","display_name":"Ehsan Kamalloo","orcid":"https://orcid.org/0000-0003-3081-8762"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ehsan Kamalloo","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071837282","display_name":"Davood Rafiei","orcid":"https://orcid.org/0000-0003-2403-0266"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Davood Rafiei","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3786","last_page":"3790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9761000275611877,"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/robustness","display_name":"Robustness (evolution)","score":0.9100348949432373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639189958572388},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6254148483276367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5385976433753967},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5138521194458008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120676159858704},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49028685688972473},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47146350145339966},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4113457202911377},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12675169110298157},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11327937245368958}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.9100348949432373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639189958572388},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6254148483276367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5385976433753967},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5138521194458008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120676159858704},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49028685688972473},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47146350145339966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4113457202911377},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12675169110298157},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11327937245368958},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557673","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557673","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1964786778","https://openalex.org/W1981590391","https://openalex.org/W2164456230","https://openalex.org/W2612177096","https://openalex.org/W2798649495","https://openalex.org/W2946504770","https://openalex.org/W2951286828","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W3034328552","https://openalex.org/W3119752913","https://openalex.org/W3133702157","https://openalex.org/W3155638005","https://openalex.org/W3174836606","https://openalex.org/W3214636190","https://openalex.org/W4212774754","https://openalex.org/W4225093372"],"related_works":["https://openalex.org/W4224920305","https://openalex.org/W3099884329","https://openalex.org/W4285322112","https://openalex.org/W3170813101","https://openalex.org/W3194819771","https://openalex.org/W4285490447","https://openalex.org/W4323066569","https://openalex.org/W2945090955","https://openalex.org/W2889705046","https://openalex.org/W3114698683"],"abstract_inverted_index":{"The":[0],"paradigm":[1],"of":[2,54,68,122],"fine-tuning":[3],"Pre-trained":[4],"Language":[5],"Models":[6],"(PLMs)":[7],"has":[8],"been":[9],"successful":[10],"in":[11,44,75,85],"Entity":[12],"Matching":[13],"(EM).":[14],"Despite":[15],"their":[16,73],"remarkable":[17],"performance,":[18],"PLMs":[19],"exhibit":[20],"tendency":[21],"to":[22,64,71,105,146],"learn":[23],"spurious":[24],"correlations":[25],"from":[26,52],"training":[27,87],"data.":[28],"In":[29],"this":[30,57],"work,":[31],"we":[32,59,113],"aim":[33],"at":[34],"investigating":[35],"whether":[36],"PLM-based":[37,123],"entity":[38],"matching":[39],"models":[40,70],"can":[41,118],"be":[42],"trusted":[43],"real-world":[45,77],"applications":[46],"where":[47],"data":[48,83,88,99],"distribution":[49],"is":[50,89,102],"different":[51],"that":[53,82,98,117,129],"training.":[55],"To":[56],"end,":[58],"design":[60],"an":[61],"evaluation":[62],"benchmark":[63],"assess":[65],"the":[66,76,86,120,142],"robustness":[67,121],"EM":[69,124,148],"facilitate":[72],"deployment":[74],"settings.":[78],"Our":[79,126],"assessments":[80],"reveal":[81],"imbalance":[84],"a":[90,107,111],"key":[91],"problem":[92],"for":[93,134],"robustness.":[94],"We":[95],"also":[96],"find":[97],"augmentation":[100],"alone":[101],"not":[103],"sufficient":[104],"make":[106],"model":[108,139,143],"robust.":[109],"As":[110],"remedy,":[112],"prescribe":[114],"simple":[115],"modifications":[116],"improve":[119],"models.":[125,149],"experiments":[127],"show":[128],"while":[130],"yielding":[131],"superior":[132],"results":[133],"in-domain":[135],"generalization,":[136],"our":[137],"proposed":[138],"significantly":[140],"improves":[141],"robustness,":[144],"compared":[145],"state-of-the-art":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}