{"id":"https://openalex.org/W4396573430","doi":"https://doi.org/10.5220/0012607500003690","title":"Scoping: Towards Streamlined Entity Collections for Multi-Sourced Entity Resolution with Self-Supervised Agents","display_name":"Scoping: Towards Streamlined Entity Collections for Multi-Sourced Entity Resolution with Self-Supervised Agents","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396573430","doi":"https://doi.org/10.5220/0012607500003690"},"language":"en","primary_location":{"id":"doi:10.5220/0012607500003690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012607500003690","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012607500003690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008015950","display_name":"Leonard Traeger","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Leonard Traeger","raw_affiliation_strings":["Department of Information Systems, University of Maryland, Baltimore County, U.S.A., --- Select a Country ---","Institute of Computer and Communication Technology (ICCT), Technical University of Cologne, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Maryland, Baltimore County, U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I79272384"]},{"raw_affiliation_string":"Institute of Computer and Communication Technology (ICCT), Technical University of Cologne, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089356465","display_name":"Andreas Behrend","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Behrend","raw_affiliation_strings":["Institute of Computer and Communication Technology (ICCT), Technical University of Cologne, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer and Communication Technology (ICCT), Technical University of Cologne, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065573453","display_name":"George Karabatis","orcid":"https://orcid.org/0000-0002-2208-0801"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Karabatis","raw_affiliation_strings":["Department of Information Systems, University of Maryland, Baltimore County, U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Maryland, Baltimore County, U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6225,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58543046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6960083246231079},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5121161937713623},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.509736955165863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4476821720600128},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4026021957397461},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35524851083755493},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3266463875770569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23400402069091797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960083246231079},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5121161937713623},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.509736955165863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4476821720600128},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4026021957397461},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35524851083755493},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3266463875770569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23400402069091797},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0012607500003690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012607500003690","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/34855","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/34855","pdf_url":"https://mdsoar.org/bitstreams/6a0ca4d7-6006-4f29-8026-b825ff0a89b3/download","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","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":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/m2geet-tgsz","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2geet-tgsz","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5220/0012607500003690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012607500003690","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1555148682","https://openalex.org/W2250539671","https://openalex.org/W2970641574","https://openalex.org/W2987228832","https://openalex.org/W2998702515","https://openalex.org/W3010144884","https://openalex.org/W3024786184","https://openalex.org/W3096174636","https://openalex.org/W3103177583","https://openalex.org/W3129166376","https://openalex.org/W3139815093","https://openalex.org/W3174181645","https://openalex.org/W4226518809","https://openalex.org/W4366729173","https://openalex.org/W4383051975","https://openalex.org/W4386159227","https://openalex.org/W4394662631"],"related_works":["https://openalex.org/W3140537242","https://openalex.org/W2130023876","https://openalex.org/W4311809271","https://openalex.org/W2188227831","https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W1517180214","https://openalex.org/W2284877871","https://openalex.org/W2082780921","https://openalex.org/W2098057544"],"abstract_inverted_index":{"Linking":[0],"multiple":[1],"entities":[2,20,24,73],"to":[3,100,108],"a":[4,8,43],"real-world":[5],"object":[6],"is":[7],"time-consuming":[9],"and":[10,28,45,55,70,77,110],"error-prone":[11],"task.":[12],"Entity":[13],"Resolution":[14],"(ER)":[15],"includes":[16],"techniques":[17],"for":[18],"vectorizing":[19],"(signature),":[21],"grouping":[22],"similar":[23],"into":[25],"partitions":[26],"(blocking),":[27],"matching":[29],"entity":[30,65,106],"pairs":[31,66],"based":[32],"on":[33,89],"specified":[34],"similarity":[35],"thresholds":[36],"(filtering).":[37],"This":[38],"paper":[39],"introduces":[40],"scoping":[41],"as":[42],"new":[44],"integral":[46],"phase":[47],"in":[48,97],"multi-sourced":[49,90],"ER":[50],"with":[51],"potentially":[52],"increased":[53],"heterogeneity":[54],"more":[56],"unlinkable":[57,72],"entities.":[58],"Scoping":[59],"reduces":[60],"the":[61,83],"space":[62],"of":[63,85],"candidate":[64],"by":[67],"ranking,":[68],"detecting,":[69],"removing":[71],"through":[74],"outlier":[75],"algorithms":[76],"reusable":[78],"self-supervised":[79],"autoencoders,":[80],"leaving":[81],"intact":[82],"set":[84],"true":[86],"linkages.":[87,114],"Evaluations":[88],"schemas":[91,98],"show":[92],"that":[93],"autoencoders":[94],"perform":[95],"best":[96],"relevant":[99],"each":[101],"other,":[102],"where":[103],"they":[104],"reduce":[105],"collections":[107],"77%":[109],"still":[111],"contain":[112],"all":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
