{"id":"https://openalex.org/W4321485607","doi":"https://doi.org/10.1145/3539597.3570383","title":"Revisiting Code Search in a Two-Stage Paradigm","display_name":"Revisiting Code Search in a Two-Stage Paradigm","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321485607","doi":"https://doi.org/10.1145/3539597.3570383"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","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/A5031338143","display_name":"Fan Hu","orcid":"https://orcid.org/0000-0002-5371-7780"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Hu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5371-7780","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350708","display_name":"Yanlin Wang","orcid":"https://orcid.org/0000-0001-7761-7269"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Wang","raw_affiliation_strings":["Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0001-7761-7269","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7625-0650","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0220-8310","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["The University of Newcastle, Sydney, NSW, China"],"raw_orcid":"https://orcid.org/0000-0002-3063-9425","affiliations":[{"raw_affiliation_string":"The University of Newcastle, Sydney, NSW, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006300825","display_name":"Shi Han","orcid":"https://orcid.org/0000-0002-0360-6089"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Han","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0360-6089","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9230-2799","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031338143"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":6.7263,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.96729872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"994","last_page":"1002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9923999905586243,"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":0.8134351968765259},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.68998122215271},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6091055274009705},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5890793800354004},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5730590224266052},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5333412289619446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4816926419734955},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.451262503862381},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4313156306743622},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4206734895706177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3854740858078003},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3611775040626526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2249218225479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134351968765259},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.68998122215271},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6091055274009705},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5890793800354004},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5730590224266052},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5333412289619446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4816926419734955},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.451262503862381},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4313156306743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4206734895706177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3854740858078003},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3611775040626526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2249218225479126},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1988686126","https://openalex.org/W2121265929","https://openalex.org/W2342696155","https://openalex.org/W2589656357","https://openalex.org/W2805788202","https://openalex.org/W3014877975","https://openalex.org/W3085514074","https://openalex.org/W3095259811","https://openalex.org/W3098605233","https://openalex.org/W3176015924","https://openalex.org/W3199225770","https://openalex.org/W4213009331","https://openalex.org/W4252076394","https://openalex.org/W6727233892"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2142795561","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2129146436","https://openalex.org/W2032507829"],"abstract_inverted_index":{"With":[0],"a":[1,87,113],"good":[2],"code":[3,10,18,90,100,118,135],"search":[4,19,75,91,101],"engine,":[5],"developers":[6],"can":[7,21,72,94],"reuse":[8],"existing":[9],"snippets":[11],"and":[12,32,44,58,107,120,138],"accelerate":[13],"software":[14],"development":[15],"process.":[16],"Current":[17],"methods":[20],"be":[22],"divided":[23],"into":[24],"two":[25],"categories:":[26],"traditional":[27],"information":[28],"retrieval":[29],"(IR)":[30],"based":[31,36],"deep":[33],"learning":[34],"(DL)":[35],"approaches.":[37],"DL-based":[38],"approaches":[39,50],"include":[40],"the":[41,45,96,144,183,188],"cross-encoder":[42,70],"paradigm":[43],"bi-encoder":[46,59,108],"paradigm.":[47],"However,":[48],"both":[49],"have":[51],"certain":[52],"limitations.":[53],"The":[54],"inference":[55],"of":[56,98,116,146,179,191],"IR-based":[57,106],"models":[60,71,109],"are":[61,65],"fast;":[62],"however,":[63],"they":[64],"not":[66,163],"accurate":[67],"enough;":[68],"while":[69],"achieve":[73],"higher":[74],"accuracy":[76,170],"but":[77,166],"consume":[78],"more":[79],"time.":[80],"In":[81],"this":[82],"work,":[83],"we":[84,129],"propose":[85],"TOSS,":[86],"two-stage":[88],"fusion":[89,155],"framework":[92],"that":[93,160],"combine":[95],"advantages":[97],"different":[99,134],"methods.":[102,156],"TOSS":[103,151,161],"first":[104],"uses":[105,122],"to":[110,142,182],"efficiently":[111],"recall":[112],"small":[114],"number":[115],"top-K":[117],"candidates,":[119],"then":[121],"fine-grained":[123],"cross-encoders":[124],"for":[125],"finer":[126],"ranking.":[127],"Furthermore,":[128],"conduct":[130],"extensive":[131],"experiments":[132],"on":[133,187],"candidate":[136],"volumes":[137],"multiple":[139],"programming":[140],"languages":[141],"verify":[143],"effectiveness":[145],"TOSS.":[147],"We":[148],"also":[149,167],"compare":[150],"with":[152,171],"six":[153],"data":[154],"Experimental":[157],"results":[158],"show":[159],"is":[162],"only":[164],"efficient,":[165],"achieves":[168],"state-of-the-art":[169],"an":[172],"overall":[173],"mean":[174],"reciprocal":[175],"ranking":[176],"(MRR)":[177],"score":[178],"0.763,":[180],"compared":[181],"best":[184],"baseline":[185],"result":[186],"CodeSearchNet":[189],"benchmark":[190],"0.713.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}