{"id":"https://openalex.org/W4385572707","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.231","title":"Natural Language to Code Translation with Execution","display_name":"Natural Language to Code Translation with Execution","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572707","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.231"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.231","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.231","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.231","pdf_url":"https://aclanthology.org/2022.emnlp-main.231.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.231.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037519114","display_name":"Freda Shi","orcid":"https://orcid.org/0009-0009-5697-449X","observed_orcids":["https://orcid.org/0009-0009-5697-449X"]},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Freda Shi","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003637850","display_name":"Daniel Fried","orcid":"https://orcid.org/0000-0002-5327-2558","observed_orcids":["https://orcid.org/0000-0002-5327-2558"]},"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":"Daniel Fried","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011974509","display_name":"Marjan Ghazvininejad","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marjan Ghazvininejad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067919401","display_name":"Luke Zettlemoyer","orcid":"https://orcid.org/0009-0008-8296-0764","observed_orcids":["https://orcid.org/0009-0008-8296-0764"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke Zettlemoyer","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102727943","display_name":"Sida I. Wang","orcid":"https://orcid.org/0000-0001-8101-8883","observed_orcids":["https://orcid.org/0000-0001-8101-8883"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sida I. Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.94,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98529082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3533","last_page":"3546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9682999849319458,"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":0.9682999849319458,"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":0.013100000098347664,"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":0.008700000122189522,"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/natural-language-to-code-translation","display_name":"natural language to code translation","score":0.9869999885559082},{"id":"https://openalex.org/keywords/program-selection","display_name":"program selection","score":0.5370000004768372},{"id":"https://openalex.org/keywords/minimum-bayes-risk-decoding","display_name":"minimum Bayes risk decoding","score":0.9110000133514404},{"id":"https://openalex.org/keywords/semantic-equivalence","display_name":"semantic equivalence","score":0.8180000185966492},{"id":"https://openalex.org/keywords/programming-language-semantics","display_name":"program semantics","score":0.5460000038146973},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8979519605636597},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.7138094902038574},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5584039092063904},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5328023433685303},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5305631160736084},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4965415596961975},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45578235387802124},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42979884147644043},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4259892702102661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40999478101730347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3339994549751282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.231","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.231","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.231","pdf_url":"https://aclanthology.org/2022.emnlp-main.231.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.11454","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.11454","pdf_url":"https://arxiv.org/pdf/2204.11454","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.11454","doi":"https://doi.org/10.48550/arxiv.2204.11454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.11454","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.231","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.231","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.231","pdf_url":"https://aclanthology.org/2022.emnlp-main.231.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572707.pdf","grobid_xml":"https://content.openalex.org/works/W4385572707.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1993666847","https://openalex.org/W2100238596","https://openalex.org/W2117086786","https://openalex.org/W2136657878","https://openalex.org/W2626778328","https://openalex.org/W2728773317","https://openalex.org/W2788109215","https://openalex.org/W2796979813","https://openalex.org/W2890431379","https://openalex.org/W2949579048","https://openalex.org/W2962728167","https://openalex.org/W2963357517","https://openalex.org/W2964315653","https://openalex.org/W2964325845","https://openalex.org/W2968297680","https://openalex.org/W2991382858","https://openalex.org/W3017094847","https://openalex.org/W3020908159","https://openalex.org/W3027871355","https://openalex.org/W3030163527","https://openalex.org/W3035058125","https://openalex.org/W3098267758","https://openalex.org/W3102020135","https://openalex.org/W3126675481","https://openalex.org/W3131945380","https://openalex.org/W3152956381","https://openalex.org/W3161457214","https://openalex.org/W3166986030","https://openalex.org/W3173777717","https://openalex.org/W3174770825","https://openalex.org/W3176456866","https://openalex.org/W3177813494","https://openalex.org/W3185341429","https://openalex.org/W3187364184","https://openalex.org/W3192405822","https://openalex.org/W3195140297","https://openalex.org/W3200285169","https://openalex.org/W4221143046","https://openalex.org/W4221161695","https://openalex.org/W4221166833","https://openalex.org/W4226287673","https://openalex.org/W4236265809"],"related_works":["https://openalex.org/W4308731473","https://openalex.org/W4389524484","https://openalex.org/W4309700390","https://openalex.org/W4416036647","https://openalex.org/W4286750487","https://openalex.org/W4226242393","https://openalex.org/W4389520032","https://openalex.org/W7203652254","https://openalex.org/W4404295467","https://openalex.org/W6891896053"],"abstract_inverted_index":{"Generative":[0],"models":[1,34,95],"of":[2,8,92,129],"code,":[3],"pretrained":[4,93],"on":[5,96,125],"large":[6],"corpora":[7],"programs,":[9],"have":[10],"shown":[11],"great":[12],"success":[13],"in":[14],"translating":[15],"natural":[16,168],"language":[17,169],"to":[18,49,132,170],"code":[19,94,171],"(Chen":[20],"et":[21,24,28],"al.,":[22,25,29],"2021;Austin":[23],"2021;":[26],"Li":[27],"2022,":[30],"inter":[31],"alia).While":[32],"these":[33],"do":[35,146],"not":[36,147],"explicitly":[37],"incorporate":[38],"program":[39,60,82,110,124,149],"semantics":[40],"(i.e.,":[41],"execution":[42,74,137,140],"results)":[43],"during":[44],"training,":[45],"they":[46],"are":[47],"able":[48],"generate":[50],"correct":[51,59],"solutions":[52],"for":[53,65,81,167],"many":[54],"problems.However,":[55],"choosing":[56],"a":[57,62,103,126],"single":[58],"from":[61,102],"generated":[63,104],"set":[64,106],"each":[66,123],"problem":[67],"remains":[68],"challenging.In":[69],"this":[70],"work,":[71],"we":[72,121],"introduce":[73],"resultbased":[75],"minimum":[76],"Bayes":[77],"risk":[78],"decoding":[79],"(MBR-EXEC)":[80],"selection":[83,159],"and":[84],"show":[85],"that":[86,112,145,152],"it":[87,162],"improves":[88,155],"the":[89,114,143],"few-shot":[90],"performance":[91],"natural-language-tocode":[97],"tasks.We":[98],"select":[99],"output":[100],"programs":[101],"candidate":[105],"by":[107],"marginalizing":[108],"over":[109,156],"implementations":[111],"share":[113],"same":[115],"semantics.Because":[116],"exact":[117],"equivalence":[118],"is":[119],"intractable,":[120],"execute":[122],"small":[127],"number":[128],"test":[130],"inputs":[131],"approximate":[133],"semantic":[134],"equivalence.Across":[135],"datasets,":[136],"or":[138],"simulated":[139],"significantly":[141],"outperforms":[142],"methods":[144],"involve":[148],"semantics.We":[150],"find":[151],"MBR-EXEC":[153],"consistently":[154],"all":[157],"execution-unaware":[158],"methods,":[160],"suggesting":[161],"as":[163],"an":[164],"effective":[165],"approach":[166],"translation.1":[172]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-08-05T00:00:00"}