{"id":"https://openalex.org/W2944246898","doi":"https://doi.org/10.1145/3338906.3340458","title":"When deep learning met code search","display_name":"When deep learning met code search","publication_year":2019,"publication_date":"2019-08-09","ids":{"openalex":"https://openalex.org/W2944246898","doi":"https://doi.org/10.1145/3338906.3340458","mag":"2944246898"},"language":"en","primary_location":{"id":"doi:10.1145/3338906.3340458","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3340458","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3340458","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3340458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046282128","display_name":"Jos\u00e9 Cambronero","orcid":"https://orcid.org/0000-0002-0713-6141"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jose Cambronero","raw_affiliation_strings":["Massachusetts Institute of Technology, USA","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402304","display_name":"Hongyu Li","orcid":"https://orcid.org/0000-0002-6518-9866"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Hongyu Li","raw_affiliation_strings":["Facebook, USA","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860729","display_name":"Seohyun Kim","orcid":"https://orcid.org/0009-0006-4371-9455"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Seohyun Kim","raw_affiliation_strings":["Facebook, USA","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569699","display_name":"Koushik Sen","orcid":"https://orcid.org/0000-0002-4539-9188"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koushik Sen","raw_affiliation_strings":["University of California at Berkeley, USA","University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101965118","display_name":"Satish Chandra","orcid":"https://orcid.org/0000-0003-2546-9000"},"institutions":[{"id":"https://openalex.org/I1321014770","display_name":"Association for Computing Machinery","ror":"https://ror.org/03wsadn68","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321014770"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Chandra","raw_affiliation_strings":["Facebook, USA","Association for Computing Machinery"],"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Association for Computing Machinery","institution_ids":["https://openalex.org/I1321014770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046282128"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.9120803,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91866658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"964","last_page":"974"},"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":0.9987000226974487,"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":0.9932000041007996,"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":0.8005091547966003},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.7324100136756897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510818362236023},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5400565266609192},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5344618558883667},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.505723237991333},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4975030720233917},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.45865532755851746},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.447745144367218},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4395887553691864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4245615601539612},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38944631814956665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3611678183078766},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3422659635543823},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27232345938682556},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2580074667930603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8005091547966003},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7324100136756897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510818362236023},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5400565266609192},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5344618558883667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.505723237991333},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4975030720233917},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.45865532755851746},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.447745144367218},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4395887553691864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4245615601539612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38944631814956665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3611678183078766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3422659635543823},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27232345938682556},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2580074667930603},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3338906.3340458","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3340458","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3340458","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.03813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03813","pdf_url":"https://arxiv.org/pdf/1905.03813","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2944246898","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1905.03813","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.03813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.03813","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3338906.3340458","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3340458","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3340458","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944246898.pdf","grobid_xml":"https://content.openalex.org/works/W2944246898.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1860267373","https://openalex.org/W1978394996","https://openalex.org/W2018430492","https://openalex.org/W2052562589","https://openalex.org/W2064675550","https://openalex.org/W2153579005","https://openalex.org/W2163922914","https://openalex.org/W2493916176","https://openalex.org/W2516621648","https://openalex.org/W2575109289","https://openalex.org/W2604536810","https://openalex.org/W2618735982","https://openalex.org/W2729710884","https://openalex.org/W2741602058","https://openalex.org/W2743945814","https://openalex.org/W2762484717","https://openalex.org/W2764024122","https://openalex.org/W2765574772","https://openalex.org/W2786676889","https://openalex.org/W2794601162","https://openalex.org/W2805494347","https://openalex.org/W2805788202","https://openalex.org/W2809671526","https://openalex.org/W2863697128","https://openalex.org/W2891000242","https://openalex.org/W2897276178","https://openalex.org/W2948702906","https://openalex.org/W2949271354","https://openalex.org/W2949888546","https://openalex.org/W2950635152","https://openalex.org/W2952842591","https://openalex.org/W2954823997","https://openalex.org/W2964150020","https://openalex.org/W3098598077","https://openalex.org/W3121414853"],"related_works":["https://openalex.org/W2968179027","https://openalex.org/W2805788202","https://openalex.org/W2794601162","https://openalex.org/W2998180104","https://openalex.org/W3111914164","https://openalex.org/W3112383693","https://openalex.org/W2516621648","https://openalex.org/W2247374552","https://openalex.org/W2042803716","https://openalex.org/W3086457636","https://openalex.org/W3011632945","https://openalex.org/W3040956736","https://openalex.org/W2949361302","https://openalex.org/W3114880807","https://openalex.org/W1486120171","https://openalex.org/W2982546493","https://openalex.org/W3099072659","https://openalex.org/W3170779537","https://openalex.org/W2952792693","https://openalex.org/W2980109654"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"multiple":[3],"recent":[4],"proposals":[5,20],"on":[6,61,151],"using":[7,14,36],"deep":[8],"neural":[9],"networks":[10,207,218],"for":[11,51,95,128,208,219],"code":[12,26,44,65,77,102,220],"search":[13],"natural":[15,28,79],"language.":[16],"Common":[17],"across":[18],"these":[19,53,137],"is":[21,87,132,175,225,235,253],"the":[22,46,99,133,161,240],"idea":[23],"of":[24,64,75,84,122,146,242],"$\\mathit{embedding}$":[25],"and":[27,34,45,67,78,98,116,124,156,244],"language":[29,80],"queries,":[30],"into":[31],"real":[32],"vectors":[33],"then":[35],"vector":[37],"distance":[38],"to":[39,88,110,126,135,149,180,192,227,230],"approximate":[40],"semantic":[41],"correlation":[42],"between":[43,239],"query.":[47],"Multiple":[48],"approaches":[49],"exist":[50],"learning":[52],"embeddings,":[54],"including":[55],"$\\mathit{unsupervised}$":[56],"techniques,":[57,69],"which":[58,70],"rely":[59],"only":[60],"a":[62,96,152,170,176,236,245],"corpus":[63,74],"examples,":[66],"$\\mathit{supervised}$":[68],"use":[71,111,127,228],"an":[72,181,193],"$\\mathit{aligned}$":[73],"paired":[76],"descriptions.":[81],"The":[82,250],"goal":[83],"this":[85,141],"supervision":[86,178,191,209,248],"produce":[89],"embeddings":[90],"that":[91,174,214],"are":[92,106],"more":[93,212,215,246],"similar":[94],"query":[97],"corresponding":[100],"desired":[101],"snippet.":[103],"Clearly,":[104],"there":[105,234],"choices":[107,138],"in":[108,164],"whether":[109],"supervised":[112],"techniques":[113,148],"at":[114,256],"all,":[115],"if":[117],"one":[118],"does,":[119],"what":[120],"sort":[121],"network":[123,165],"training":[125,155],"supervision.":[129],"This":[130],"paper":[131],"first":[134],"evaluate":[136],"systematically.":[139],"To":[140,159],"end,":[142],"we":[143,167],"assembled":[144],"implementations":[145],"state-of-the-art":[147],"run":[150],"common":[153,226],"platform,":[154],"evaluation":[157,186,251],"corpora.":[158],"explore":[160],"design":[162,172],"space":[163],"complexity,":[166],"also":[168],"introduced":[169],"new":[171],"point":[173],"$\\mathit{minimal}$":[177],"extension":[179],"existing":[182,194],"unsupervised":[183,195],"technique.":[184],"Our":[185],"shows":[187],"that:":[188],"1.":[189],"adding":[190],"technique":[196],"can":[197,210],"improve":[198],"performance,":[199],"though":[200],"not":[201],"necessarily":[202],"by":[203],"much;":[204],"2.":[205],"simple":[206],"be":[211],"effective":[213],"sophisticated":[216],"sequence-based":[217],"search;":[221],"3.":[222],"while":[223],"it":[224],"docstrings":[229,243],"carry":[231],"out":[232],"supervision,":[233],"sizeable":[237],"gap":[238],"effectiveness":[241],"query-appropriate":[247],"corpus.":[249],"dataset":[252],"now":[254],"available":[255],"arXiv:1908.09804":[257]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}