{"id":"https://openalex.org/W2889467844","doi":"https://doi.org/10.18653/v1/d18-1111","title":"Retrieval-Based Neural Code Generation","display_name":"Retrieval-Based Neural Code Generation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889467844","doi":"https://doi.org/10.18653/v1/d18-1111","mag":"2889467844"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1111","pdf_url":"https://www.aclweb.org/anthology/D18-1111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1111.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007056150","display_name":"Shirley Anugrah Hayati","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shirley Anugrah Hayati","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091011631","display_name":"Rapha\u00ebl Olivier","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raphael Olivier","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013689091","display_name":"Pravalika Avvaru","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pravalika Avvaru","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078519761","display_name":"Pengcheng Yin","orcid":"https://orcid.org/0000-0003-2739-1032"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengcheng Yin","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027233041","display_name":"Anthony Tomasic","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Tomasic","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007056150"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":14.7672,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.98896321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"925","last_page":"930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976999759674072,"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":0.882472038269043},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.744109570980072},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6337437033653259},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5793934464454651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500746965408325},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49808406829833984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48615261912345886},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4847571551799774},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47488850355148315},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.45833829045295715},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.43851256370544434},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4156450033187866},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.411419153213501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07856440544128418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.882472038269043},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.744109570980072},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6337437033653259},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5793934464454651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500746965408325},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49808406829833984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48615261912345886},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4847571551799774},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47488850355148315},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.45833829045295715},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.43851256370544434},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4156450033187866},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.411419153213501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07856440544128418},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":1,"locations":[{"id":"doi:10.18653/v1/d18-1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1111","pdf_url":"https://www.aclweb.org/anthology/D18-1111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1111","pdf_url":"https://www.aclweb.org/anthology/D18-1111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1197061222","display_name":"SHF: Small: Open-domain, Data-driven Code Synthesis from Natural Language","funder_award_id":"1815287","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889467844.pdf","grobid_xml":"https://content.openalex.org/works/W2889467844.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2165666205","https://openalex.org/W2170732969","https://openalex.org/W2175619924","https://openalex.org/W2242083635","https://openalex.org/W2295159694","https://openalex.org/W2751262944","https://openalex.org/W2757592053","https://openalex.org/W2788330850","https://openalex.org/W2962728167","https://openalex.org/W2963357517","https://openalex.org/W2963617989","https://openalex.org/W2963655793","https://openalex.org/W2963794306","https://openalex.org/W2963829526","https://openalex.org/W2963841178","https://openalex.org/W2964165364","https://openalex.org/W2964284687","https://openalex.org/W2964308564","https://openalex.org/W2964325845","https://openalex.org/W3104874136"],"related_works":["https://openalex.org/W4310447811","https://openalex.org/W2165004968","https://openalex.org/W3122369893","https://openalex.org/W4282813445","https://openalex.org/W3012064729","https://openalex.org/W2955426500","https://openalex.org/W2388254906","https://openalex.org/W4200321676","https://openalex.org/W3049398420","https://openalex.org/W2979271470"],"abstract_inverted_index":{"In":[0],"models":[1],"to":[2,27,33,38,57,76,114,135],"generate":[3,28],"program":[4],"source":[5],"code":[6,12,30,61,66,130],"from":[7],"natural":[8],"language,":[9],"representing":[10],"this":[11],"in":[13,116],"a":[14,19,34,47,64,80],"tree":[15],"structure":[16],"has":[17],"been":[18],"common":[20],"approach.":[21],"However,":[22],"existing":[23,60],"methods":[24],"often":[25],"fail":[26],"complex":[29,42],"correctly":[31],"due":[32],"lack":[35],"of":[36,90,105],"ability":[37],"memorize":[39],"large":[40],"and":[41],"structures.":[43],"We":[44,120],"introduce":[45],"RECODE,":[46],"method":[48],"based":[49],"on":[50,128],"subtree":[51,113],"retrieval":[52],"that":[53,73,93,107,122],"makes":[54],"it":[55],"possible":[56],"explicitly":[58],"reference":[59],"examples":[62],"within":[63],"neural":[65],"generation":[67,131],"model.":[68],"First,":[69],"we":[70,87,101],"retrieve":[71],"sentences":[72,78],"are":[74],"similar":[75],"input":[77],"using":[79],"dynamicprogramming-based":[81],"sentence":[82],"similarity":[83],"scoring":[84],"method.":[85],"Next,":[86],"extract":[88],"n-grams":[89],"action":[91,112],"sequences":[92],"build":[94],"the":[95,103,109,117,126],"associated":[96],"abstract":[97],"syntax":[98],"tree.":[99],"Finally,":[100],"increase":[102],"probability":[104],"actions":[106],"cause":[108],"retrieved":[110],"n-gram":[111],"be":[115],"predicted":[118],"code.":[119],"show":[121],"our":[123],"approach":[124],"improves":[125],"performance":[127],"two":[129],"tasks":[132],"by":[133],"up":[134],"+2.6":[136],"BLEU.":[137],"1":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}