{"id":"https://openalex.org/W2964315653","doi":"https://doi.org/10.1145/3196398.3196408","title":"Learning to mine aligned code and natural language pairs from stack overflow","display_name":"Learning to mine aligned code and natural language pairs from stack overflow","publication_year":2018,"publication_date":"2018-05-28","ids":{"openalex":"https://openalex.org/W2964315653","doi":"https://doi.org/10.1145/3196398.3196408","mag":"2964315653"},"language":"en","primary_location":{"id":"doi:10.1145/3196398.3196408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196398.3196408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Mining Software Repositories","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/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":["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/A5019923149","display_name":"Bowen Deng","orcid":"https://orcid.org/0000-0003-1447-842X"},"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":"Bowen Deng","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/A5056966994","display_name":"Edgar Chen","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":"Edgar Chen","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/A5050821883","display_name":"Bogdan Vasilescu","orcid":"https://orcid.org/0000-0003-4418-5783"},"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":"Bogdan Vasilescu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":18.0552,"has_fulltext":false,"cited_by_count":203,"citation_normalized_percentile":{"value":0.99436545,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996999979019165,"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":0.8580645322799683},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5885681509971619},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5877880454063416},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5375968813896179},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5186969041824341},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49401599168777466},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.487884521484375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45046091079711914},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.43707790970802307},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.43352165818214417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42781034111976624},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.42004379630088806},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.416271448135376},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.41580528020858765},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37711989879608154},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.11249712109565735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580645322799683},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5885681509971619},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5877880454063416},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5375968813896179},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5186969041824341},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49401599168777466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.487884521484375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45046091079711914},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.43707790970802307},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.43352165818214417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42781034111976624},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.42004379630088806},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.416271448135376},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.41580528020858765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37711989879608154},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.11249712109565735}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3196398.3196408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196398.3196408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1588986231","https://openalex.org/W1655078475","https://openalex.org/W1753482797","https://openalex.org/W1860267373","https://openalex.org/W1902237438","https://openalex.org/W1916559533","https://openalex.org/W1972141422","https://openalex.org/W1973719497","https://openalex.org/W1974020522","https://openalex.org/W1977678951","https://openalex.org/W1997358723","https://openalex.org/W2010608861","https://openalex.org/W2023925487","https://openalex.org/W2033705196","https://openalex.org/W2034209539","https://openalex.org/W2054855378","https://openalex.org/W2095705004","https://openalex.org/W2103305545","https://openalex.org/W2117228548","https://openalex.org/W2125943921","https://openalex.org/W2126793110","https://openalex.org/W2130942839","https://openalex.org/W2136189984","https://openalex.org/W2143960295","https://openalex.org/W2156981320","https://openalex.org/W2158396456","https://openalex.org/W2242083635","https://openalex.org/W2251957808","https://openalex.org/W2257123346","https://openalex.org/W2298285108","https://openalex.org/W2344444819","https://openalex.org/W2406533925","https://openalex.org/W2466147406","https://openalex.org/W2516621648","https://openalex.org/W2577255746","https://openalex.org/W2592864539","https://openalex.org/W2593390416","https://openalex.org/W2728773317","https://openalex.org/W2740220421","https://openalex.org/W2788306232","https://openalex.org/W2884681705","https://openalex.org/W2962728167","https://openalex.org/W2963266340","https://openalex.org/W2963545046","https://openalex.org/W2963617989","https://openalex.org/W2964121744","https://openalex.org/W2964165364","https://openalex.org/W2964284687","https://openalex.org/W2964308564","https://openalex.org/W3098281910","https://openalex.org/W4240795705","https://openalex.org/W4289255588"],"related_works":["https://openalex.org/W2344367508","https://openalex.org/W2571988079","https://openalex.org/W4389751695","https://openalex.org/W4310447811","https://openalex.org/W2165004968","https://openalex.org/W2320787857","https://openalex.org/W3086207785","https://openalex.org/W2098629748","https://openalex.org/W2969229669","https://openalex.org/W3012064729"],"abstract_inverted_index":{"For":[0],"tasks":[1],"like":[2],"code":[3,8,11,31,62,77,141],"synthesis":[4],"from":[5,109],"natural":[6,27],"language,":[7],"retrieval,":[9],"and":[10,30,52,88,125,140,163,176,208],"summarization,":[12],"data-driven":[13],"models":[14,22],"have":[15,56],"shown":[16],"great":[17],"promise.":[18],"However,":[19,64],"creating":[20],"these":[21],"require":[23],"parallel":[24],"data":[25,46,108],"between":[26,138],"language":[28,207],"(NL)":[29],"with":[32,59,75],"fine-grained":[33],"alignments.":[34],"Stack":[35],"Overflow":[36],"(SO)":[37],"is":[38],"a":[39,45,73,101,131,150,186,219],"promising":[40],"source":[41],"to":[42,104,134,218,232],"create":[43],"such":[44],"set:":[47],"the":[48,70,76,79,89,92,119,122,136,154,170,203],"questions":[49],"are":[50,82,147,198,230],"diverse":[51],"most":[53],"of":[54,72,91,114,121,156,189,222],"them":[55],"corresponding":[57],"answers":[58],"high":[60],"quality":[61,155],"snippets.":[63],"existing":[65,179],"heuristic":[66],"methods":[67],"(e.g.,":[68],"pairing":[69],"title":[71],"post":[74],"in":[78,85],"accepted":[80],"answer)":[81],"limited":[83],"both":[84],"their":[86],"coverage":[87,175],"correctness":[90],"NL-code":[93,158,216],"pairs":[94],"obtained.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99,193,229],"propose":[100],"novel":[102],"method":[103,172],"mine":[105],"high-quality":[106],"aligned":[107],"SO":[110],"using":[111,142,161,184],"two":[112],"sets":[113],"features:":[115],"hand-crafted":[116],"features":[117,127,146],"considering":[118],"structure":[120],"extracted":[123],"snippets,":[124],"correspondence":[126],"obtained":[128],"by":[129],"training":[130,202],"probabilistic":[132],"model":[133],"capture":[135],"correlation":[137],"NL":[139],"neural":[143],"networks.":[144],"These":[145],"fed":[148],"into":[149],"classifier":[151,204],"that":[152,169,195],"determines":[153],"mined":[157],"pairs.":[159],"Experiments":[160],"Python":[162],"Java":[164],"as":[165],"test":[166],"beds":[167],"show":[168],"proposed":[171],"greatly":[173],"expands":[174],"accuracy":[177],"over":[178],"mining":[180,217],"methods,":[181],"even":[182,200],"when":[183,201],"only":[185],"small":[187],"number":[188],"labeled":[190],"examples.":[191],"Further,":[192],"find":[194],"reasonable":[196],"results":[197],"achieved":[199],"on":[205,210],"one":[206],"testing":[209],"another,":[211],"showing":[212],"promise":[213],"for":[214,227],"scaling":[215],"wide":[220],"variety":[221],"programming":[223],"languages":[224],"beyond":[225],"those":[226],"which":[228],"able":[231],"annotate":[233],"data.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}