{"id":"https://openalex.org/W3171492007","doi":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","display_name":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3171492007","doi":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","mag":"3171492007"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.nlp4prog-1.8","doi":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","pdf_url":"https://aclanthology.org/2021.nlp4prog-1.8.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 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.nlp4prog-1.8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001884614","display_name":"Gabriel Orlanski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Orlanski","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038646656","display_name":"Alex Gittens","orcid":"https://orcid.org/0000-0003-3482-0157","observed_orcids":["https://orcid.org/0000-0003-3482-0157"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Gittens","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":1.2397,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79823529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.8241999745368958,"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":0.8241999745368958,"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":0.13459999859333038,"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":0.015599999576807022,"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/stack-overflow","display_name":"Stack Overflow","score":0.6729999780654907},{"id":"https://openalex.org/keywords/programming-question-answering","display_name":"programming question answering","score":0.7720000147819519},{"id":"https://openalex.org/keywords/intent-recognition","display_name":"intent classification","score":0.527999997138977},{"id":"https://openalex.org/keywords/bart","display_name":"BART","score":0.8309999704360962},{"id":"https://openalex.org/keywords/cheating-behavior","display_name":"cheating","score":0.46399998664855957},{"id":"https://openalex.org/keywords/corpus-construction","display_name":"corpus construction","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764595746994019},{"id":"https://openalex.org/C2778024590","wikidata":"https://www.wikidata.org/wiki/Q2357432","display_name":"Cheating","level":2,"score":0.7417949438095093},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.678593635559082},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6480477452278137},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6305660605430603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6159939765930176},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5893750190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5833032727241516},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.543181836605072},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5402324795722961},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5284041166305542},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4464612603187561},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13305190205574036},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.09591615200042725},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08878955245018005},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08858007192611694},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2021.nlp4prog-1.8","doi":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","pdf_url":"https://aclanthology.org/2021.nlp4prog-1.8.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 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.04447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04447","pdf_url":"https://arxiv.org/pdf/2106.04447","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":"mag:3171492007","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.04447","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.04447","doi":"https://doi.org/10.48550/arxiv.2106.04447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.04447","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.nlp4prog-1.8","doi":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nlp4prog-1.8","pdf_url":"https://aclanthology.org/2021.nlp4prog-1.8.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 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)","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/W3171492007.pdf","grobid_xml":"https://content.openalex.org/works/W3171492007.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1496189301","https://openalex.org/W2047237057","https://openalex.org/W2154652894","https://openalex.org/W2163274265","https://openalex.org/W2511108736","https://openalex.org/W2626778328","https://openalex.org/W2768282280","https://openalex.org/W2788306232","https://openalex.org/W2796979813","https://openalex.org/W2888925928","https://openalex.org/W2889467844","https://openalex.org/W2890431379","https://openalex.org/W2890867094","https://openalex.org/W2912624765","https://openalex.org/W2945102109","https://openalex.org/W2949215742","https://openalex.org/W2962728167","https://openalex.org/W2963357517","https://openalex.org/W2963617989","https://openalex.org/W2964315653","https://openalex.org/W2964325845","https://openalex.org/W2970004377","https://openalex.org/W2979826702","https://openalex.org/W2982399380","https://openalex.org/W2997847174","https://openalex.org/W3017094847","https://openalex.org/W3022192152","https://openalex.org/W3030163527","https://openalex.org/W3098605233","https://openalex.org/W3123221944","https://openalex.org/W3126675481","https://openalex.org/W3131945380","https://openalex.org/W3153348131","https://openalex.org/W3156012351","https://openalex.org/W4236265809","https://openalex.org/W4393721841","https://openalex.org/W4394638297","https://openalex.org/W6893675597"],"related_works":["https://openalex.org/W3201849546","https://openalex.org/W4382703364","https://openalex.org/W7028488605","https://openalex.org/W7171497249","https://openalex.org/W3194055078","https://openalex.org/W2969174677","https://openalex.org/W4415067971","https://openalex.org/W4415971881","https://openalex.org/W7131844606","https://openalex.org/W4289255588"],"abstract_inverted_index":{"Answering":[0],"a":[1,21,57,84],"programming":[2],"question":[3,27,50],"using":[4,104],"only":[5],"its":[6,134],"title":[7],"is":[8,14,127],"difficult":[9],"as":[10],"salient":[11],"contextual":[12],"information":[13],"omitted.Based":[15],"on":[16],"this":[17,64,94],"observation,":[18],"we":[19,52,120],"present":[20],"corpus":[22],"of":[23,61,70,103,114],"over":[24],"40,000":[25],"StackOverflow":[26],"texts":[28],"to":[29,55,82,123],"be":[30],"used":[31],"in":[32],"conjunction":[33],"with":[34,78,93],"their":[35],"corresponding":[36],"intents":[37],"from":[38],"the":[39,47,74,79,105,111,115],"CoNaLa":[40,76,91],"dataset":[41],"(Yin":[42],"et":[43],"al.,":[44],"2018).Using":[45],"both":[46],"intent":[48],"and":[49,97,107,132],"body,":[51],"use":[53],"BART":[54,126],"establish":[56],"baseline":[58],"BLEU":[59,86,112],"score":[60,113],"34.35":[62],"for":[63],"new":[65],"task.We":[66],"find":[67,98],"further":[68],"improvements":[69],"2.8%":[71],"by":[72,118],"combining":[73],"mined":[75,108],"data":[77,81,96,109],"labeled":[80],"achieve":[83],"35.32":[85],"score.We":[87],"evaluate":[88],"prior":[89,116],"stateof-the-art":[90],"models":[92],"additional":[95],"that":[99,125],"our":[100],"proposed":[101],"method":[102],"body":[106],"beats":[110],"state-of-the-art":[117],"71.96%.Finally,":[119],"perform":[121],"ablations":[122],"demonstrate":[124],"an":[128],"unsupervised":[129],"multimodal":[130],"learner":[131],"examine":[133],"extractive":[135],"behavior.1":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2021-06-22T00:00:00"}