{"id":"https://openalex.org/W4389158487","doi":"https://doi.org/10.1145/3611643.3616369","title":"Efficient Text-to-Code Retrieval with Cascaded Fast and Slow Transformer Models","display_name":"Efficient Text-to-Code Retrieval with Cascaded Fast and Slow Transformer Models","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389158487","doi":"https://doi.org/10.1145/3611643.3616369"},"language":"en","primary_location":{"id":"doi:10.1145/3611643.3616369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","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/A5104211341","display_name":"Akhilesh Deepak Gotmare","orcid":"https://orcid.org/0000-0001-6502-0350"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akhilesh Deepak Gotmare","raw_affiliation_strings":["Salesforce AI Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6502-0350","affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608756","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-1405-2034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junnan Li","raw_affiliation_strings":["Salesforce AI Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1405-2034","affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005443526","display_name":"Shafiq Joty","orcid":"https://orcid.org/0000-0002-9222-2641"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shafiq Joty","raw_affiliation_strings":["Salesforce AI Research, Singapore, USA"],"raw_orcid":"https://orcid.org/0000-0002-9222-2641","affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Singapore, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074834854","display_name":"Steven C. H. Hoi","orcid":"https://orcid.org/0000-0002-4584-3453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven C.H. Hoi","raw_affiliation_strings":["Salesforce AI Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4584-3453","affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104211341"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3453,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86048564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8739475607872009},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.6450580954551697},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5832432508468628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5590819716453552},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5401763916015625},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5156453847885132},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5044518709182739},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45451968908309937},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4543938934803009},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45017266273498535},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4192473590373993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39870911836624146},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3574952483177185},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3204592168331146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.259380042552948},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1931876242160797},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16729092597961426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739475607872009},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.6450580954551697},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5832432508468628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5590819716453552},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5401763916015625},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5156453847885132},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5044518709182739},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45451968908309937},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4543938934803009},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45017266273498535},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4192473590373993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39870911836624146},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3574952483177185},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3204592168331146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.259380042552948},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1931876242160797},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16729092597961426},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3611643.3616369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2260194779","https://openalex.org/W2387719207","https://openalex.org/W2624871570","https://openalex.org/W2794601162","https://openalex.org/W2805788202","https://openalex.org/W2913340405","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2968179027","https://openalex.org/W2982596739","https://openalex.org/W2990138404","https://openalex.org/W2999343753","https://openalex.org/W3005296017","https://openalex.org/W3005680577","https://openalex.org/W3015001695","https://openalex.org/W3021397474","https://openalex.org/W3036320503","https://openalex.org/W3038572442","https://openalex.org/W3086007799","https://openalex.org/W3098468692","https://openalex.org/W3108032709","https://openalex.org/W3123221944","https://openalex.org/W3155146092","https://openalex.org/W3171668871","https://openalex.org/W3177813494","https://openalex.org/W3180230246","https://openalex.org/W3184735396","https://openalex.org/W3192256856","https://openalex.org/W3198188208","https://openalex.org/W3204588463","https://openalex.org/W4210743562","https://openalex.org/W4226182655","https://openalex.org/W4226278401","https://openalex.org/W4226485558","https://openalex.org/W4283009931","https://openalex.org/W4284664028","https://openalex.org/W4285483825","https://openalex.org/W4287024925","https://openalex.org/W4288057765","https://openalex.org/W4288280764","https://openalex.org/W4288805334","https://openalex.org/W4311887664","https://openalex.org/W4367860052","https://openalex.org/W4376652621","https://openalex.org/W4384302749","https://openalex.org/W4394638297"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W1484298060","https://openalex.org/W2153253904","https://openalex.org/W3169572532","https://openalex.org/W2096374501","https://openalex.org/W4379381520","https://openalex.org/W2131684755","https://openalex.org/W2794433798","https://openalex.org/W1716487511"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,49,97,113,162,179],"semantic":[3,31],"code":[4,15,20,32],"search":[5,8,33,60],"or":[6],"text-to-code":[7,59],"is":[9,75,143],"to":[10,38,77,93,122,174],"retrieve":[11],"a":[12,23,29,70,79,88,132],"semantically":[13],"relevant":[14],"snippet":[16],"from":[17,102],"an":[18,40,55,155],"existing":[19,35],"database":[21],"using":[22],"natural":[24],"language":[25],"query.":[26],"When":[27],"constructing":[28],"practical":[30],"system,":[34],"approaches":[36],"fail":[37],"provide":[39],"optimal":[41],"balance":[42],"between":[43],"retrieval":[44,84],"speed":[45],"and":[46,57,65,127,147],"the":[47,50,95,98,103,109,125,169,175],"relevance":[48],"retrieved":[51],"results.":[52],"We":[53],"propose":[54,121],"efficient":[56,146],"effective":[58],"framework":[61],"with":[62,136,154],"cascaded":[63,141],"fast":[64,71,83,104,126],"slow":[66,89,128],"models,":[67],"in":[68,118],"which":[69],"transformer":[72,134],"encoder":[73,135],"model":[74,92,129],"learned":[76],"optimize":[78],"scalable":[80],"index":[81],"for":[82],"followed":[85],"by":[86],"learning":[87],"classification-based":[90],"re-ranking":[91],"improve":[94],"accuracy":[96],"top":[99],"K":[100],"results":[101,153],"retrieval.":[105],"To":[106],"further":[107],"reduce":[108],"high":[110],"memory":[111],"cost":[112],"deploying":[114],"two":[115],"separate":[116],"models":[117],"practice,":[119],"we":[120],"jointly":[123],"train":[124],"based":[130],"on":[131,168],"single":[133],"shared":[137],"parameters.":[138],"Empirically":[139],"our":[140],"method":[142],"not":[144],"only":[145],"scalable,":[148],"but":[149],"also":[150],"achieves":[151],"state-of-the-art":[152,177],"average":[156],"mean":[157],"reciprocal":[158],"ranking":[159],"(MRR)":[160],"score":[161],"0.7795":[163],"(across":[164],"6":[165],"programming":[166],"languages)":[167],"CodeSearchNet":[170],"benchmark":[171],"as":[172],"opposed":[173],"prior":[176],"result":[178],"0.744":[180],"MRR.":[181],"Our":[182],"codebase":[183],"can":[184],"be":[185],"found":[186],"at":[187],"this":[188],"link.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
