{"id":"https://openalex.org/W4281972940","doi":"https://doi.org/10.1145/3514221.3517843","title":"DB-BERT: A Database Tuning Tool that \"Reads the Manual\"","display_name":"DB-BERT: A Database Tuning Tool that \"Reads the Manual\"","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281972940","doi":"https://doi.org/10.1145/3514221.3517843"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517843","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517843","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087259526","display_name":"Immanuel Trummer","orcid":"https://orcid.org/0000-0002-7203-2349"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Immanuel Trummer","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087259526"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":6.492,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97466476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9966999888420105,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9794999957084656,"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":0.8774452209472656},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7751531600952148},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6665027141571045},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6029534935951233},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.503675639629364},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4825996160507202},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47290265560150146},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45110711455345154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3718387186527252},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34662383794784546},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18502825498580933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8774452209472656},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7751531600952148},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6665027141571045},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6029534935951233},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.503675639629364},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4825996160507202},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47290265560150146},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45110711455345154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3718387186527252},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34662383794784546},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18502825498580933},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517843","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3514221.3517843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517843","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281972940.pdf","grobid_xml":"https://content.openalex.org/works/W4281972940.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1997783781","https://openalex.org/W2612690371","https://openalex.org/W2613206411","https://openalex.org/W2889503624","https://openalex.org/W2896457183","https://openalex.org/W2944240329","https://openalex.org/W2948513753","https://openalex.org/W2970148517","https://openalex.org/W2970851599","https://openalex.org/W2979826702","https://openalex.org/W3011085391","https://openalex.org/W3029327553","https://openalex.org/W3099273181","https://openalex.org/W3100925961","https://openalex.org/W3139827290","https://openalex.org/W3150554837","https://openalex.org/W4287826606","https://openalex.org/W4288269198"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W4386541577"],"abstract_inverted_index":{"DB-BERT":[0,37,72,139,165,178],"is":[1,179],"a":[2,85],"database":[3,26,87,112,131,157],"tuning":[4,104,132],"tool":[5],"that":[6,110,118],"exploits":[7],"information":[8],"gained":[9],"via":[10],"natural":[11,63],"language":[12,41,64],"analysis":[13],"of":[14,103,127,177],"manuals":[15],"and":[16,77,89,95,147,151,160],"other":[17],"relevant":[18],"text":[19,23,48,128],"documents.":[20],"It":[21],"uses":[22],"to":[24,29,61,74,80,99,106],"identify":[25],"system":[27,88,113],"parameters":[28],"tune":[30],"as":[31,33,133,154,156],"well":[32,155],"recommended":[34,67],"parameter":[35,169],"values.":[36],"applies":[38],"large,":[39],"pre-trained":[40],"models":[42],"(specifically,":[43],"the":[44,101,111,167],"BERT":[45],"model)":[46],"for":[47,84,135],"analysis.":[49],"During":[50],"an":[51],"initial":[52],"training":[53],"phase,":[54],"it":[55],"fine-tunes":[56],"model":[57],"weights":[58],"in":[59],"order":[60],"translate":[62],"hints":[65,79],"into":[66],"settings.":[68],"At":[69],"run":[70,152],"time,":[71],"learns":[73],"aggregate,":[75],"adapt,":[76],"prioritize":[78],"achieve":[81],"optimal":[82],"performance":[83],"specific":[86],"benchmark.":[90],"Both":[91],"phases":[92],"are":[93],"iterative":[94],"use":[96],"reinforcement":[97],"learning":[98],"guide":[100],"selection":[102],"settings":[105,109,117,170],"evaluate":[107],"(penalizing":[108],"rejects":[114],"while":[115],"rewarding":[116],"improve":[119],"performance).":[120],"In":[121,162],"our":[122],"experiments,":[123],"we":[124],"leverage":[125],"hundreds":[126],"documents":[129],"about":[130],"input":[134],"DB-BERT.":[136],"We":[137],"compare":[138],"against":[140],"various":[141],"baselines,":[142],"considering":[143],"different":[144],"benchmarks":[145],"(TPC-C":[146],"TPC-H),":[148],"metrics":[149],"(throughput":[150],"time),":[153],"systems":[158],"(Postgres":[159],"MySQL).":[161],"all":[163,172],"cases,":[164],"finds":[166],"best":[168],"among":[171],"compared":[173],"methods.":[174],"The":[175],"code":[176],"available":[180],"online":[181],"at":[182],"https://itrummer.github.io/dbbert/.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}