{"id":"https://openalex.org/W3014451403","doi":"https://doi.org/10.1109/saner48275.2020.9054840","title":"Are the Code Snippets What We Are Searching for? A Benchmark and an Empirical Study on Code Search with Natural-Language Queries","display_name":"Are the Code Snippets What We Are Searching for? A Benchmark and an Empirical Study on Code Search with Natural-Language Queries","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3014451403","doi":"https://doi.org/10.1109/saner48275.2020.9054840","mag":"3014451403"},"language":"en","primary_location":{"id":"doi:10.1109/saner48275.2020.9054840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner48275.2020.9054840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043183427","display_name":"Shuhan Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhan Yan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101794556","display_name":"Hang Yu","orcid":"https://orcid.org/0000-0002-3805-0009"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107464006","display_name":"Yuting Chen","orcid":"https://orcid.org/0009-0004-6696-052X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045672909","display_name":"Beijun Shen","orcid":"https://orcid.org/0000-0001-8370-3956"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beijun Shen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083048049","display_name":"Lingxiao Jiang","orcid":"https://orcid.org/0000-0002-4336-8548"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lingxiao Jiang","raw_affiliation_strings":["Singapore Management University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9939000010490417,"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":0.9900000095367432,"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":0.8748365640640259},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5905354619026184},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.586300790309906},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5726802945137024},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5592275261878967},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5440652966499329},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.5146945118904114},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47521597146987915},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44693171977996826},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.4234144985675812},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.415189653635025},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4126794636249542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4072742462158203},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35900527238845825},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32661765813827515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32466012239456177},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.32109588384628296},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2852811813354492},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.23044249415397644},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.227108895778656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748365640640259},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5905354619026184},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.586300790309906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5726802945137024},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5592275261878967},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5440652966499329},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.5146945118904114},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47521597146987915},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44693171977996826},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.4234144985675812},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.415189653635025},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4126794636249542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4072742462158203},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35900527238845825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32661765813827515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32466012239456177},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.32109588384628296},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2852811813354492},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.23044249415397644},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.227108895778656},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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":2,"locations":[{"id":"doi:10.1109/saner48275.2020.9054840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner48275.2020.9054840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-6978","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=6978&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/SANER48275.2020.9054840","raw_type":"Edited Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W41491511","https://openalex.org/W1566018662","https://openalex.org/W1614298861","https://openalex.org/W1812927916","https://openalex.org/W1860267373","https://openalex.org/W1986601961","https://openalex.org/W1993786160","https://openalex.org/W1995650922","https://openalex.org/W2006291142","https://openalex.org/W2008353316","https://openalex.org/W2008693679","https://openalex.org/W2031289572","https://openalex.org/W2042803716","https://openalex.org/W2060055745","https://openalex.org/W2064675550","https://openalex.org/W2115733813","https://openalex.org/W2118805943","https://openalex.org/W2130942839","https://openalex.org/W2144211451","https://openalex.org/W2145732224","https://openalex.org/W2175297521","https://openalex.org/W2203629570","https://openalex.org/W2246363069","https://openalex.org/W2247374552","https://openalex.org/W2298285108","https://openalex.org/W2342696155","https://openalex.org/W2387719207","https://openalex.org/W2492006053","https://openalex.org/W2516621648","https://openalex.org/W2548718128","https://openalex.org/W2585840180","https://openalex.org/W2604794021","https://openalex.org/W2612300213","https://openalex.org/W2620682708","https://openalex.org/W2739978563","https://openalex.org/W2754109047","https://openalex.org/W2794601162","https://openalex.org/W2795013376","https://openalex.org/W2902938971","https://openalex.org/W2944123291","https://openalex.org/W2950577311","https://openalex.org/W2963391195","https://openalex.org/W2963879841","https://openalex.org/W2963935794","https://openalex.org/W2964315653","https://openalex.org/W2969540611","https://openalex.org/W2973529529","https://openalex.org/W2998907024","https://openalex.org/W3100105221","https://openalex.org/W3104874136","https://openalex.org/W4233045210","https://openalex.org/W4235641765","https://openalex.org/W4241089335","https://openalex.org/W4394638297","https://openalex.org/W6633661181","https://openalex.org/W6639050008","https://openalex.org/W6649133229","https://openalex.org/W6661024068","https://openalex.org/W6679436768","https://openalex.org/W6768003788"],"related_works":["https://openalex.org/W2904997879","https://openalex.org/W2390085541","https://openalex.org/W2921460747","https://openalex.org/W4205744693","https://openalex.org/W2097696338","https://openalex.org/W2969257295","https://openalex.org/W2082765019","https://openalex.org/W4312736744","https://openalex.org/W4303450757","https://openalex.org/W4226230447"],"abstract_inverted_index":{"Code":[0],"search":[1,48,131,177,199],"methods,":[2,132],"especially":[3],"those":[4,82],"that":[5,53,139,203],"allow":[6],"programmers":[7],"to":[8,24],"raise":[9],"queries":[10,147,210,218],"in":[11,19,50,59,120],"a":[12,125,137,152],"natural":[13],"language,":[14],"plays":[15],"an":[16],"important":[17],"role":[18],"software":[20],"development.":[21],"It":[22],"helps":[23],"improve":[25],"programmers'":[26],"productivity":[27],"by":[28],"returning":[29],"sample":[30],"code":[31,47,130,161,176,198],"snippets":[32],"from":[33],"the":[34,51,61,70,79,85,187,190],"Internet":[35],"and/or":[36],"source-code":[37],"repositories":[38],"for":[39,73,87,128,156,209,217],"their":[40,109],"natural-language":[41,55,146],"queries.":[42,56],"Meanwhile,":[43],"there":[44],"are":[45,90,206],"many":[46],"methods":[49,83,98,178,205],"literature":[52],"support":[54],"Difficulties":[57],"exist":[58],"recognizing":[60],"strengths":[62,195],"and":[63,68,84,95,107,115,151,171,193,214,222],"weaknesses":[64],"of":[65,81,141,154,189,196],"each":[66,197],"method":[67],"choosing":[69],"right":[71],"one":[72],"different":[74,100],"usage":[75],"scenarios,":[76],"because":[77],"(1)":[78],"implementations":[80],"datasets":[86,102],"evaluating":[88],"them":[89],"usually":[91],"not":[92],"publicly":[93],"available,":[94],"(2)":[96],"some":[97],"leverage":[99],"training":[101],"or":[103],"auxiliary":[104],"data":[105],"sources":[106],"thus":[108],"effectiveness":[110],"cannot":[111],"be":[112,117],"fairly":[113],"measured":[114],"may":[116],"negatively":[118],"affected":[119],"practical":[121],"uses.":[122,225],"To":[123],"build":[124],"common":[126],"ground":[127,149],"measuring":[129],"this":[133],"paper":[134],"builds":[135],"CosBench,":[136],"dataset":[138,192],"consists":[140],"1000":[142],"projects,":[143],"52":[144],"code-independent":[145],"with":[148],"truths,":[150],"set":[153],"scripts":[155],"calculating":[157],"four":[158,167],"metrics":[159],"on":[160,179,211,219],"research":[162],"results.":[163],"We":[164,201],"have":[165],"evaluated":[166],"IR":[168],"(Information":[169],"Retrieval)-based":[170],"two":[172],"DL":[173],"(Deep":[174],"Learning)-based":[175],"CosBench.":[180],"The":[181],"empirical":[182],"evaluation":[183],"results":[184],"clearly":[185],"show":[186],"usefulness":[188],"CosBench":[191],"various":[194],"method.":[200],"found":[202],"DL-based":[204],"more":[207],"suitable":[208],"reusing":[212],"code,":[213],"IR-based":[215],"ones":[216],"resolving":[220],"bugs":[221],"learning":[223],"API":[224]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}