{"id":"https://openalex.org/W4315630389","doi":"https://doi.org/10.1109/paap56126.2022.10010698","title":"Do Not Have Enough Data? An Easy Data Augmentation for Code Summarization","display_name":"Do Not Have Enough Data? An Easy Data Augmentation for Code Summarization","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4315630389","doi":"https://doi.org/10.1109/paap56126.2022.10010698"},"language":"en","primary_location":{"id":"doi:10.1109/paap56126.2022.10010698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap56126.2022.10010698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 13th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","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/A5090581386","display_name":"Zixuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixuan Song","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038253295","display_name":"Xiuwei Shang","orcid":"https://orcid.org/0009-0009-6660-9947"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuwei Shang","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544068","display_name":"Mengxuan Li","orcid":"https://orcid.org/0000-0003-4411-4790"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxuan Li","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418997","display_name":"Rong Chen","orcid":"https://orcid.org/0000-0001-5848-6398"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423958","display_name":"Hui Li","orcid":"https://orcid.org/0000-0003-1923-0669"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018071549","display_name":"Shikai Guo","orcid":"https://orcid.org/0000-0002-8554-6365"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikai Guo","raw_affiliation_strings":["The College of Information Science and Technology,Dalian Maritime University,Dalian,China","Dalian Maritime University, The College of Information Science and Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"The College of Information Science and Technology,Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Dalian Maritime University, The College of Information Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090581386"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":null,"apc_paid":null,"fwci":1.2126,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8467037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9853000044822693,"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":0.9793000221252441,"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":0.8740664124488831},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6510505080223083},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6112269759178162},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5974920392036438},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.49502772092819214},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.487989604473114},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47277382016181946},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4425656795501709},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42025333642959595},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.41961729526519775},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4114115238189697},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3302488625049591},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3008185923099518},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2797691226005554},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.26437729597091675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740664124488831},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6510505080223083},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6112269759178162},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5974920392036438},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.49502772092819214},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.487989604473114},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47277382016181946},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4425656795501709},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42025333642959595},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.41961729526519775},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4114115238189697},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3302488625049591},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3008185923099518},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2797691226005554},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26437729597091675}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/paap56126.2022.10010698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap56126.2022.10010698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 13th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2728773317","https://openalex.org/W2951652751","https://openalex.org/W2963545917","https://openalex.org/W3014755496","https://openalex.org/W3034689979","https://openalex.org/W3130959173","https://openalex.org/W6776237760"],"related_works":["https://openalex.org/W2344367508","https://openalex.org/W2571988079","https://openalex.org/W2980220905","https://openalex.org/W2986478207","https://openalex.org/W4312706861","https://openalex.org/W2098629748","https://openalex.org/W2144528247","https://openalex.org/W4244608052","https://openalex.org/W4312050194","https://openalex.org/W1992074508"],"abstract_inverted_index":{"Code":[0],"comments":[1,28,90],"improve":[2,16],"the":[3,17,20,41,47,54,86,98,101,106,109,117,120,177,184,187],"readability":[4],"and":[5,15,23,52,59,91,134,167],"intelligibility":[6],"of":[7,19,43,56,100,108,130,179,201],"codes,":[8],"which":[9,38,84],"can":[10,190],"help":[11],"developers":[12,44],"understand":[13],"programs":[14],"efficiency":[18,42,55],"software":[21,36,57],"maintenance":[22,58],"evolution":[24],"process.":[25],"Unfortunately,":[26],"code":[27,51,67,89,93,159],"are":[29,113,173],"often":[30,103],"mismatched,":[31],"missing,":[32],"or":[33],"outdated":[34],"in":[35,199],"projects,":[37],"negatively":[39],"affects":[40],"to":[45,78,94,175,196],"infer":[46],"functionality":[48],"from":[49,171],"source":[50,66,92],"affect":[53],"evolution.":[60],"To":[61,147],"solve":[62],"this":[63,149],"problem,":[64],"many":[65],"summarization":[68],"algorithms":[69,189],"have":[70,152],"been":[71],"proposed.":[72],"However,":[73],"these":[74],"methods":[75],"usually":[76],"try":[77],"collect":[79],"a":[80,127,154,193],"large":[81,128],"data":[82,122,135,142,155],"set":[83],"contains":[85],"mapping":[87],"between":[88],"train":[95],"models.":[96],"Hence,":[97],"effectiveness":[99],"models":[102,182],"rely":[104],"on":[105,165,183],"quality":[107],"training":[110,118,132,141],"data.":[111],"There":[112],"two":[114],"limitations":[115],"for":[116,143,158],"sets:":[119],"insufficient":[121],"collection":[123],"limitation":[124,138],"(i.e.,":[125,139,205],"generate":[126,140],"amount":[129],"noises-free":[131],"data)":[133],"distribution":[136],"bias":[137],"infrequently":[144],"used":[145],"methods).":[146],"address":[148],"issues,":[150],"we":[151],"proposed":[153],"augmentation":[156],"method":[157],"comments,":[160],"named":[161],"CDA-CS.":[162,180],"Extensive":[163],"experiments":[164],"Java":[166],"Python":[168],"projects":[169],"collected":[170],"GitHub":[172],"conducted":[174],"evaluate":[176],"performance":[178],"Training":[181],"augmented":[185],"dataset,":[186],"state-of-the-art":[188],"easily":[191],"get":[192],"further":[194],"1.37%":[195],"2.24%":[197],"improvement":[198],"terms":[200],"different":[202],"evaluation":[203],"metrics":[204],"BLEU-4,":[206],"METEOR,":[207],"ROUGH_L)":[208],"with":[209],"no":[210],"additional":[211],"cost.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
