{"id":"https://openalex.org/W4409403843","doi":"https://doi.org/10.1145/3711542.3711548","title":"SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries","display_name":"SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4409403843","doi":"https://doi.org/10.1145/3711542.3711548"},"language":"en","primary_location":{"id":"doi:10.1145/3711542.3711548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711548","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","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/10.1145/3711542.3711548","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111241692","display_name":"Quan Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quan Mai","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Arkansas, Fayetteville, Arkansas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032138644","display_name":"Susan Gauch","orcid":"https://orcid.org/0000-0001-5538-7343"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan Gauch","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Arkansas, Fayetteville, Arkansas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":null,"display_name":"Douglas Adams","orcid":"https://orcid.org/0009-0008-3875-7793"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Adams","raw_affiliation_strings":["Department of Sociology and Criminology, University of Arkansas, Fayetteville, Arkansas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Sociology and Criminology, University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111241692"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":1.029,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80146244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9950000047683716,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9950000047683716,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9937999844551086,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.7783671617507935},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5955869555473328},{"id":"https://openalex.org/keywords/and-inverter-graph","display_name":"And-inverter graph","score":0.48251983523368835},{"id":"https://openalex.org/keywords/boolean-circuit","display_name":"Boolean circuit","score":0.4687357544898987},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4580269455909729},{"id":"https://openalex.org/keywords/boolean-function","display_name":"Boolean function","score":0.4114643931388855},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3715756833553314},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16649574041366577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15379247069358826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783671617507935},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5955869555473328},{"id":"https://openalex.org/C196836630","wikidata":"https://www.wikidata.org/wiki/Q4753279","display_name":"And-inverter graph","level":4,"score":0.48251983523368835},{"id":"https://openalex.org/C141796577","wikidata":"https://www.wikidata.org/wiki/Q837479","display_name":"Boolean circuit","level":3,"score":0.4687357544898987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4580269455909729},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.4114643931388855},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3715756833553314},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16649574041366577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15379247069358826}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711542.3711548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711548","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711542.3711548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711548","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7470362337","display_name":null,"funder_award_id":"OIA-1946391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409403843.pdf","grobid_xml":"https://content.openalex.org/works/W4409403843.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1980515494","https://openalex.org/W2068632118","https://openalex.org/W2970641574","https://openalex.org/W3035599593","https://openalex.org/W3099700870","https://openalex.org/W3201254286","https://openalex.org/W4205332217","https://openalex.org/W4252076394","https://openalex.org/W4385570281"],"related_works":["https://openalex.org/W2150974517","https://openalex.org/W2060171268","https://openalex.org/W3144510369","https://openalex.org/W1976822807","https://openalex.org/W2728195892","https://openalex.org/W3029381898","https://openalex.org/W4241453319","https://openalex.org/W2246807618","https://openalex.org/W4248224315","https://openalex.org/W2169792446"],"abstract_inverted_index":{"We":[0],"introduce":[1],"SetBERT,":[2],"a":[3,63,98],"fine-tuned":[4],"BERT-based":[5,74],"model":[6],"designed":[7],"to":[8,97,108],"enhance":[9],"query":[10],"embeddings":[11],"for":[12,32,83],"set":[13],"operations":[14],"and":[15,25,40,59],"Boolean":[16],"logic":[17],"queries,":[18,34],"such":[19],"as":[20],"Intersection":[21],"(AND),":[22],"Difference":[23],"(NOT),":[24],"Union":[26],"(OR).SetBERT":[27],"significantly":[28,93],"improves":[29],"retrieval":[30,42],"performance":[31,82,106],"logic-structured":[33],"an":[35,47],"area":[36],"where":[37],"both":[38],"traditional":[39],"neural":[41],"methods":[43],"typically":[44],"underperform.We":[45],"propose":[46],"innovative":[48],"use":[49],"of":[50],"inversed-contrastive":[51],"loss,":[52],"focusing":[53],"on":[54],"identifying":[55],"the":[56,109,118],"negative":[57],"sentence,":[58],"fine-tuning":[60,76],"BERT":[61],"with":[62,77],"dataset":[64],"generated":[65],"via":[66],"prompt":[67],"GPT.Furthermore,":[68],"we":[69],"demonstrate":[70],"that,":[71],"unlike":[72],"other":[73],"models,":[75],"triplet":[78],"loss":[79],"actually":[80],"degrades":[81],"this":[84],"specific":[85],"task.Our":[86],"experiments":[87],"reveal":[88],"that":[89],"SetBERT-base":[90],"not":[91],"only":[92,116],"outperforms":[94],"BERT-base":[95],"(up":[96],"63%":[99],"improvement":[100],"in":[101],"Recall)":[102],"but":[103],"also":[104],"achieves":[105],"comparable":[107],"much":[110],"larger":[111],"BERT-large":[112],"model,":[113],"despite":[114],"being":[115],"one-third":[117],"size.":[119],"CCS":[120],"Concepts":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}