{"id":"https://openalex.org/W4410356765","doi":"https://doi.org/10.1145/3672608.3707946","title":"SC-Block++: A Blocking Algorithm Based on Adaptive Flood Regularization","display_name":"SC-Block++: A Blocking Algorithm Based on Adaptive Flood Regularization","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356765","doi":"https://doi.org/10.1145/3672608.3707946"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707946","source":null,"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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117539741","display_name":"Arthur Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arthur Ning","raw_affiliation_strings":["Erasmus University Rotterdam, Rotterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0006-9221-5069","affiliations":[{"raw_affiliation_string":"Erasmus University Rotterdam, Rotterdam, Netherlands","institution_ids":["https://openalex.org/I913958620"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044867921","display_name":"Flavius Fr\u0103sincar","orcid":"https://orcid.org/0000-0002-8031-758X"},"institutions":[{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Flavius Frasincar","raw_affiliation_strings":["Erasmus University Rotterdam, Rotterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8031-758X","affiliations":[{"raw_affiliation_string":"Erasmus University Rotterdam, Rotterdam, Netherlands","institution_ids":["https://openalex.org/I913958620"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047426731","display_name":"Tarmo Robal","orcid":"https://orcid.org/0000-0002-7396-8843"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Tarmo Robal","raw_affiliation_strings":["Tallinn University of Technology, Tallinn, Estonia"],"raw_orcid":"https://orcid.org/0000-0002-7396-8843","affiliations":[{"raw_affiliation_string":"Tallinn University of Technology, Tallinn, Estonia","institution_ids":["https://openalex.org/I111112146"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86435245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1258","last_page":"1266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9958999752998352,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9901999831199646,"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/blocking","display_name":"Blocking (statistics)","score":0.786499559879303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6043847799301147},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5960384607315063},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.565171480178833},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5265672206878662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20369082689285278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1374969184398651},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11441227793693542},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06784161925315857}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.786499559879303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043847799301147},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5960384607315063},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.565171480178833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5265672206878662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20369082689285278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1374969184398651},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11441227793693542},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06784161925315857}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3672608.3707946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707946","source":null,"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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.eur.nl:openaire/ba436f81-7ae0-4a95-a1b3-95987d678eab","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/ba436f81-7ae0-4a95-a1b3-95987d678eab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ning, A, Frasincar, F & Robal, T 2025, SC-Block++ : A Blocking Algorithm Based on Adaptive Flood Regularization. in 40th Annual ACM Symposium on Applied Computing, SAC 2025. Association for Computing Machinery (ACM), Proceedings of the ACM Symposium on Applied Computing, pp. 1258-1266, 40th Annual ACM Symposium on Applied Computing, SAC 2025, Catania, Italy, 31/03/25. https://doi.org/10.1145/3672608.3707946","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3672608.3707946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707946","source":null,"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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410356765.pdf","grobid_xml":"https://content.openalex.org/works/W4410356765.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2031250218","https://openalex.org/W2034978228","https://openalex.org/W2128661986","https://openalex.org/W2601251286","https://openalex.org/W2607294481","https://openalex.org/W2618530766","https://openalex.org/W2747329762","https://openalex.org/W2798649495","https://openalex.org/W2963518130","https://openalex.org/W2970641574","https://openalex.org/W2992897306","https://openalex.org/W2998702515","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3099734810","https://openalex.org/W3123375411","https://openalex.org/W3197468999","https://openalex.org/W3213822864","https://openalex.org/W4206410067"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2392835431","https://openalex.org/W2051487156","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2073681303","https://openalex.org/W2353762239","https://openalex.org/W66314852"],"abstract_inverted_index":{"The":[0],"rapid":[1],"surge":[2],"in":[3,118],"the":[4,16,82,115,135,139,160,164,193],"number":[5],"of":[6,19,84,126,138,163],"Web":[7,38],"shops":[8],"presents":[9],"a":[10,44,54,59,69,73,96,103,124,130,150],"challenge":[11],"for":[12],"consumers:":[13],"navigating":[14],"through":[15],"vast":[17],"amount":[18],"stores":[20],"and":[21,68,122,157,171,180],"products":[22],"available.":[23],"Therefore,":[24],"entity":[25,41],"resolution":[26,42],"has":[27],"become":[28],"an":[29,93,119],"important":[30],"task":[31],"to":[32,63,77,95,113,154,158,169,186],"aggregate":[33],"product":[34,66,116],"information":[35],"across":[36],"different":[37,177],"shops.":[39],"As":[40],"is":[43,184],"computationally":[45,60,74],"demanding":[46],"process,":[47],"its":[48],"pipelines":[49],"are":[50],"divided":[51],"into":[52],"two:":[53],"blocking":[55,98,195],"phase,":[56],"which":[57],"uses":[58],"cheap":[61],"method":[62,76,152],"select":[64],"candidate":[65,85,127,188],"pairs,":[67],"matching":[70,79],"phase":[71],"with":[72],"expensive":[75],"identify":[78],"pairs":[80,128,189],"from":[81],"set":[83,125],"pairs.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90],"propose":[91],"SC-Block++,":[92],"extension":[94],"state-of-the-art":[97],"algorithm":[99],"SC-Block.":[100],"SC-Block":[101],"utilizes":[102],"RoBERTa":[104,140],"base":[105,141],"transformer":[106,142],"model,":[107],"trained":[108],"using":[109,129],"Supervised":[110],"Contrastive":[111],"Learning,":[112],"position":[114],"records":[117],"embedding":[120],"space,":[121],"produces":[123],"nearest-neighbour":[131],"search.":[132],"We":[133,166],"extend":[134],"training":[136],"procedure":[137],"model":[143],"by":[144],"incorporating":[145],"Adaptive":[146],"Flood":[147],"Regularization":[148],"(AdaFlood),":[149],"regularization":[151],"aimed":[153],"prevent":[155],"overfitting":[156],"improve":[159],"generalization":[161],"performance":[162],"model.":[165],"compare":[167],"SC-Block++":[168,183],"SC-Block,":[170],"other":[172,194],"benchmark":[173],"methods":[174],"on":[175],"three":[176],"data":[178],"sets,":[179],"find":[181],"that":[182],"able":[185],"construct":[187],"more":[190],"effectively":[191],"than":[192],"schemes.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}