{"id":"https://openalex.org/W4384659755","doi":"https://doi.org/10.1145/3539618.3591860","title":"Improving Programming Q&A with Neural Generative Augmentation","display_name":"Improving Programming Q&A with Neural Generative Augmentation","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384659755","doi":"https://doi.org/10.1145/3539618.3591860"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","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/A5003172820","display_name":"Suthee Chaidaroon","orcid":"https://orcid.org/0000-0002-3655-5708"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suthee Chaidaroon","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3655-5708","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708644","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0003-2573-2171"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2573-2171","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006306368","display_name":"Shruti Subramaniyam","orcid":"https://orcid.org/0009-0003-4603-2921"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shruti Subramaniyam","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4603-2921","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006573523","display_name":"Jeffrey Svajlenko","orcid":"https://orcid.org/0000-0001-9738-7421"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Svajlenko","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9738-7421","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055777277","display_name":"Tanya Shourya","orcid":"https://orcid.org/0009-0000-3870-3009"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Shourya","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0000-3870-3009","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086488087","display_name":"Iman Keivanloo","orcid":"https://orcid.org/0000-0001-9552-6950"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iman Keivanloo","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9552-6950","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102725323","display_name":"Ria Joy","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ria Joy","raw_affiliation_strings":["Amazon Web Service, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0002-7239-3598","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13911268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3390","last_page":"3394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9983999729156494,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9886999726295471,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961522340774536},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6796518564224243},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5688183903694153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448532104492188},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4948398470878601},{"id":"https://openalex.org/keywords/programming-domain","display_name":"Programming domain","score":0.48476332426071167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48377200961112976},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4834362268447876},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.4740709364414215},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46748870611190796},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4287976622581482},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42632415890693665},{"id":"https://openalex.org/keywords/inductive-programming","display_name":"Inductive programming","score":0.42407840490341187},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.419151246547699},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3572569489479065},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19292619824409485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961522340774536},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6796518564224243},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5688183903694153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448532104492188},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4948398470878601},{"id":"https://openalex.org/C119263510","wikidata":"https://www.wikidata.org/wiki/Q7248501","display_name":"Programming domain","level":4,"score":0.48476332426071167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48377200961112976},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4834362268447876},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.4740709364414215},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46748870611190796},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4287976622581482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42632415890693665},{"id":"https://openalex.org/C50033165","wikidata":"https://www.wikidata.org/wiki/Q15712089","display_name":"Inductive programming","level":3,"score":0.42407840490341187},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.419151246547699},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3572569489479065},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19292619824409485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1986601961","https://openalex.org/W2121265929","https://openalex.org/W2122401044","https://openalex.org/W2167527590","https://openalex.org/W2247374552","https://openalex.org/W2516621648","https://openalex.org/W2741561716","https://openalex.org/W2805788202","https://openalex.org/W2887364112","https://openalex.org/W2981852735","https://openalex.org/W3151388396","https://openalex.org/W3155638432","https://openalex.org/W3208981019","https://openalex.org/W3210866099","https://openalex.org/W4205371973","https://openalex.org/W4221166942","https://openalex.org/W4246531378","https://openalex.org/W4288089799","https://openalex.org/W6636625392"],"related_works":["https://openalex.org/W2161156675","https://openalex.org/W3201070945","https://openalex.org/W2792951589","https://openalex.org/W27046826","https://openalex.org/W2160823258","https://openalex.org/W2089642402","https://openalex.org/W2201388310","https://openalex.org/W2129576602","https://openalex.org/W2037532900","https://openalex.org/W2114533692"],"abstract_inverted_index":{"Knowledge-intensive":[0],"programming":[1,21,46,143,175],"Q&A":[2],"is":[3,49],"an":[4,84],"active":[5],"research":[6],"area":[7],"in":[8,18],"industry.":[9],"Its":[10],"application":[11,172],"boosts":[12],"developer":[13],"productivity":[14],"by":[15,72,145,150],"aiding":[16],"developers":[17],"quickly":[19],"finding":[20],"answers":[22],"from":[23],"the":[24,30,59,66,90,123,129,136,140,147,156],"vast":[25],"amount":[26],"of":[27,110],"information":[28],"on":[29,58,128,139,155],"Internet.":[31],"In":[32,115],"this":[33],"study,":[34],"we":[35,119],"propose":[36],"ProQANS":[37,48,71],"and":[38,42,93,169],"its":[39,170],"variants":[40],"ReProQANS":[41,69,111,121],"ReAugProQANS":[43,134],"to":[44,64,88,101,106,152,165,173],"tackle":[45],"Q&A.":[47],"a":[50,77,95],"neural":[51],"search":[52],"approach":[53],"that":[54],"leverages":[55],"unlabeled":[56],"data":[57],"Internet":[60],"(such":[61],"as":[62,113],"StackOverflow)":[63],"mitigate":[65],"cold-start":[67],"problem.":[68],"extends":[70],"utilizing":[73],"reformulated":[74],"queries":[75],"with":[76],"novel":[78,96],"triplet":[79,98],"loss.":[80],"We":[81],"further":[82],"use":[83],"auxiliary":[85],"generative":[86],"model":[87,149],"augment":[89],"training":[91],"queries,":[92,105],"design":[94],"dual":[97],"loss":[99],"function":[100],"adapt":[102],"these":[103],"generated":[104],"build":[107],"another":[108],"variant":[109],"termed":[112],"ReAugProQANS.":[114],"our":[116],"empirical":[117],"experiments,":[118],"show":[120],"has":[122,135],"best":[124],"performance":[125,138],"when":[126],"evaluated":[127],"in-domain":[130],"test":[131],"set,":[132],"while":[133],"superior":[137],"out-of-domain":[141],"real":[142,174],"questions,":[144],"outperforming":[146],"state-of-the-art":[148],"up":[151],"477%":[153],"lift":[154],"MRR":[157],"metric":[158],"respectively.":[159],"The":[160],"results":[161],"suggest":[162],"their":[163],"robustness":[164],"previously":[166],"unseen":[167],"questions":[168],"wide":[171],"questions.":[176]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}