{"id":"https://openalex.org/W4387869001","doi":"https://doi.org/10.1145/3630009","title":"The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks","display_name":"The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387869001","doi":"https://doi.org/10.1145/3630009"},"language":"en","primary_location":{"id":"doi:10.1145/3630009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630009","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5102446495","display_name":"Jiho Shin","orcid":"https://orcid.org/0000-0001-8829-3773"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jiho Shin","raw_affiliation_strings":["York University, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045306475","display_name":"Moshi Wei","orcid":"https://orcid.org/0000-0003-1659-1960"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Moshi Wei","raw_affiliation_strings":["York University, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108814327","display_name":"Junjie Wang","orcid":"https://orcid.org/0000-0002-9941-6713"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014381743","display_name":"Lin Shi","orcid":"https://orcid.org/0000-0003-1476-7213"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shi","raw_affiliation_strings":["School of Software, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326214","display_name":"Song Wang","orcid":"https://orcid.org/0000-0003-0617-2877"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["York University, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102446495"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":3.1651,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9306566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"2","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9972000122070312,"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":0.9972000122070312,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9878000020980835,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9807999730110168,"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":0.863412618637085},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.6426806449890137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6267796158790588},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6126706600189209},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5628308057785034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5217538475990295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5148707628250122},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47835296392440796},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4426654577255249},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40913480520248413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32838261127471924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863412618637085},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.6426806449890137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6267796158790588},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6126706600189209},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5628308057785034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5217538475990295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5148707628250122},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47835296392440796},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4426654577255249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40913480520248413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32838261127471924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630009","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3456977075","display_name":null,"funder_award_id":"62332001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5717671410","display_name":null,"funder_award_id":"62272445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2050372846","https://openalex.org/W2087016914","https://openalex.org/W2096451472","https://openalex.org/W2097001189","https://openalex.org/W2242083635","https://openalex.org/W2259472270","https://openalex.org/W2599674900","https://openalex.org/W2600463316","https://openalex.org/W2604799547","https://openalex.org/W2607303097","https://openalex.org/W2612690371","https://openalex.org/W2788306232","https://openalex.org/W2888017562","https://openalex.org/W2888559334","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2910096450","https://openalex.org/W2919115771","https://openalex.org/W2922234936","https://openalex.org/W2924700250","https://openalex.org/W2962728167","https://openalex.org/W2963357517","https://openalex.org/W2963617989","https://openalex.org/W2963794306","https://openalex.org/W2964315653","https://openalex.org/W2964325845","https://openalex.org/W2970004377","https://openalex.org/W2981852735","https://openalex.org/W2997847174","https://openalex.org/W3004796001","https://openalex.org/W3007157104","https://openalex.org/W3081454995","https://openalex.org/W3086007799","https://openalex.org/W3089307846","https://openalex.org/W3093464584","https://openalex.org/W3098281910","https://openalex.org/W3103702776","https://openalex.org/W3119507053","https://openalex.org/W3126675481","https://openalex.org/W3142154623","https://openalex.org/W3155146092","https://openalex.org/W3155256780","https://openalex.org/W3160700180","https://openalex.org/W3161997752","https://openalex.org/W3193990408","https://openalex.org/W3195421019","https://openalex.org/W3209771704","https://openalex.org/W4226075195","https://openalex.org/W4238846128","https://openalex.org/W4252684946","https://openalex.org/W4255386139","https://openalex.org/W4285600327","https://openalex.org/W4288089799","https://openalex.org/W4288095001","https://openalex.org/W4289365316","https://openalex.org/W4292295224","https://openalex.org/W4292779060","https://openalex.org/W4300870773","https://openalex.org/W4308643032","https://openalex.org/W6676028428","https://openalex.org/W6689008102","https://openalex.org/W6692563993","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W2798329462","https://openalex.org/W2163672025","https://openalex.org/W2258184894","https://openalex.org/W4313563760","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4231058664","https://openalex.org/W2147744656"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"has":[3],"been":[4,79],"increasingly":[5],"used":[6,146],"in":[7,25,104,209,235],"a":[8,49,53,59,179],"variety":[9],"of":[10,31,88,118,154,170,206,218,274],"domains,":[11],"while":[12],"solving":[13],"ML":[14,42,64,105,125,147,157,176,196,278],"programming":[15,33,65,95,106,126,158],"tasks":[16,96,197,201],"poses":[17],"unique":[18],"challenges":[19],"due":[20],"to":[21,62,114],"the":[22,26,29,84,116,219,271],"fundamental":[23],"difference":[24,205],"nature":[27],"and":[28,102,139,167,290],"construct":[30],"general":[32,94],"tasks,":[34,177,279],"especially":[35],"for":[36,257,277,284],"developers":[37,248,254],"who":[38],"do":[39,231],"not":[40,232],"have":[41,78,233],"backgrounds.":[43],"Automatic":[44],"code":[45,50,75,121,136,172,189,221,245,251,275,282],"generation":[46,76,122,137,173,190,229,276,283],"that":[47,86],"produces":[48],"snippet":[51],"from":[52,266],"natural":[54],"language":[55],"description":[56],"can":[57,246],"be":[58],"promising":[60],"technique":[61],"accelerate":[63],"tasks.":[66,107,127,159],"In":[67,108],"recent":[68],"years,":[69],"although":[70],"many":[71],"deep":[72],"learning-based":[73],"neural":[74,120,135,171],"models":[77,123,138,174,191,230],"proposed":[80],"with":[81,149,178,202,255],"high":[82],"accuracy,":[83],"fact":[85],"most":[87],"them":[89],"are":[90],"mainly":[91],"evaluated":[92],"on":[93,124,143,175,195,199],"calls":[97],"into":[98,286],"question":[99],"their":[100,141],"effectiveness":[101,117],"usefulness":[103],"this":[109],"article,":[110],"we":[111,131],"set":[112],"out":[113],"investigate":[115],"existing":[119],"For":[128],"our":[129,267],"analysis,":[130],"select":[132],"six":[133],"state-of-the-art":[134],"evaluate":[140],"performance":[142],"four":[144],"widely":[145],"libraries,":[148],"newly":[150],"created":[151],"83K":[152],"pairs":[153],"natural-language":[155],"described":[156],"Our":[160],"empirical":[161],"study":[162,269],"reveals":[163,270],"some":[164],"good,":[165],"bad,":[166],"missing":[168,272],"aspects":[169,273],"few":[180],"major":[181],"ones":[182],"listed":[183],"below.":[184],"(":[185,212,225,240,261],"Good":[186,241],")":[187,214,227,242,263],"Neural":[188],"perform":[192],"significantly":[193],"better":[194],"than":[198,216],"non-ML":[200],"an":[203],"average":[204],"10.6":[207],"points":[208],"BLEU-4":[210],"scores.":[211],"Bad":[213,226],"More":[215],"80%":[217],"generated":[220,244],"is":[222],"semantically":[223],"incorrect.":[224],"Code":[228],"significance":[234],"improving":[236],"developers\u2019":[237],"completion":[238],"time.":[239],"The":[243,264],"help":[247],"write":[249],"correct":[250,259],"by":[252],"providing":[253],"clues":[256],"using":[258],"APIs.":[260],"Missing":[262],"observation":[265],"user":[268],"e.g.,":[280],"decomposing":[281],"divide-and-conquer":[285],"API":[287,291],"sequence":[288],"identification":[289],"usage":[292],"generation.":[293]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}