{"id":"https://openalex.org/W2809170625","doi":"https://doi.org/10.1145/3183440.3195021","title":"Learning to mine parallel natural language/source code corpora from stack overflow","display_name":"Learning to mine parallel natural language/source code corpora from stack overflow","publication_year":2018,"publication_date":"2018-05-27","ids":{"openalex":"https://openalex.org/W2809170625","doi":"https://doi.org/10.1145/3183440.3195021","mag":"2809170625"},"language":"en","primary_location":{"id":"doi:10.1145/3183440.3195021","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183440.3195021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","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":0.6226,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68195624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.880650520324707},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.732385516166687},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6974342465400696},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6111195683479309},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5799785256385803},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5627115964889526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.544303297996521},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5369271039962769},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4324502646923065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4248805642127991},{"id":"https://openalex.org/keywords/heap","display_name":"Heap (data structure)","score":0.42155370116233826},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41904351115226746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41678181290626526},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.33398014307022095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.880650520324707},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.732385516166687},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6974342465400696},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6111195683479309},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5799785256385803},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5627115964889526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.544303297996521},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5369271039962769},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4324502646923065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4248805642127991},{"id":"https://openalex.org/C134757568","wikidata":"https://www.wikidata.org/wiki/Q274089","display_name":"Heap (data structure)","level":2,"score":0.42155370116233826},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41904351115226746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41678181290626526},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33398014307022095}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183440.3195021","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183440.3195021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1655078475","https://openalex.org/W1860267373","https://openalex.org/W1974020522","https://openalex.org/W2023925487","https://openalex.org/W2158396456","https://openalex.org/W2257123346","https://openalex.org/W2466147406","https://openalex.org/W2516621648","https://openalex.org/W2592864539","https://openalex.org/W2963617989","https://openalex.org/W2964284687"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2091301346","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W2789551765"],"abstract_inverted_index":{"For":[0],"tasks":[1],"like":[2],"code":[3,8,11,31],"synthesis":[4],"from":[5,78],"natural":[6,27],"language,":[7],"retrieval,":[9],"and":[10,30,58,98,114,119,132],"summarization,":[12],"data-driven":[13],"models":[14,22],"have":[15],"shown":[16],"great":[17],"promise.":[18],"However,":[19],"creating":[20],"these":[21],"requires":[23],"parallel":[24],"data":[25,46,77],"between":[26,112],"language":[28],"(NL)":[29],"with":[32],"fine-grained":[33],"alignments.":[34],"Stack":[35],"Overflow":[36],"(SO)":[37],"is":[38],"a":[39,45,71,82,104,142],"promising":[40],"source":[41],"to":[42,73,108],"create":[43],"such":[44],"set":[47],"but":[48],"existing":[49,135],"heuristic":[50],"methods":[51],"are":[52],"limited":[53],"both":[54],"in":[55],"their":[56],"coverage":[57,131],"the":[59,62,92,95,110,126],"correctness":[60],"of":[61,87,94,145],"NL-code":[63],"pairs":[64],"obtained.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"method":[72,128],"mine":[74],"high-quality":[75],"aligned":[76],"SO":[79],"by":[80,102],"training":[81,103],"classifier":[83],"using":[84,117,140],"two":[85],"sets":[86],"features:":[88],"hand-crafted":[89],"features":[90,100],"considering":[91],"structure":[93],"extracted":[96],"snippets,":[97],"correspondence":[99],"obtained":[101],"neural":[105],"network":[106],"model":[107],"capture":[109],"correlation":[111],"NL":[113],"code.":[115],"Experiments":[116],"Python":[118],"Java":[120],"as":[121],"test":[122],"beds":[123],"show":[124],"that":[125],"proposed":[127],"greatly":[129],"expands":[130],"accuracy":[133],"over":[134],"mining":[136],"methods,":[137],"even":[138],"when":[139],"only":[141],"small":[143],"number":[144],"labeled":[146],"examples.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}