{"id":"https://openalex.org/W4409796558","doi":"https://doi.org/10.1109/apsec65559.2024.00033","title":"Improving Code Search with Hard Negative Sampling Based on Fine-tuning","display_name":"Improving Code Search with Hard Negative Sampling Based on Fine-tuning","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4409796558","doi":"https://doi.org/10.1109/apsec65559.2024.00033"},"language":"en","primary_location":{"id":"doi:10.1109/apsec65559.2024.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsec65559.2024.00033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 31st Asia-Pacific Software Engineering Conference (APSEC)","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/A5007017628","display_name":"Hande Dong","orcid":"https://orcid.org/0000-0003-0074-2664"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hande Dong","raw_affiliation_strings":["International Digital Economy Academy,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638844","display_name":"Jiayi Lin","orcid":"https://orcid.org/0000-0001-8811-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayi Lin","raw_affiliation_strings":["International Digital Economy Academy,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350708","display_name":"Yanlin Wang","orcid":"https://orcid.org/0000-0001-7761-7269"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Wang","raw_affiliation_strings":["Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053168506","display_name":"Yichong Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichong Leng","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362815","display_name":"Jiawei Chen","orcid":"https://orcid.org/0000-0002-4752-2629"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Chen","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101680201","display_name":"Yutao Xie","orcid":"https://orcid.org/0009-0003-3889-6631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Xie","raw_affiliation_strings":["International Digital Economy Academy,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy,Shenzhen,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007017628"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71720596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9315000176429749,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9315000176429749,"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":0.7311294674873352},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5009546279907227},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43713587522506714},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40207406878471375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2715264558792114},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09530839323997498},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07386544346809387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311294674873352},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5009546279907227},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43713587522506714},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40207406878471375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2715264558792114},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09530839323997498},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07386544346809387},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsec65559.2024.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsec65559.2024.00033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 31st Asia-Pacific Software Engineering Conference (APSEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1981829374","https://openalex.org/W2536015822","https://openalex.org/W2648699835","https://openalex.org/W2788306232","https://openalex.org/W2794601162","https://openalex.org/W2805788202","https://openalex.org/W2842511635","https://openalex.org/W2902618648","https://openalex.org/W2968179027","https://openalex.org/W2971190479","https://openalex.org/W2999343753","https://openalex.org/W3035524453","https://openalex.org/W3093604544","https://openalex.org/W3098605233","https://openalex.org/W3138081324","https://openalex.org/W3155146092","https://openalex.org/W3157758108","https://openalex.org/W3170092793","https://openalex.org/W3173787059","https://openalex.org/W3176015924","https://openalex.org/W4221166942","https://openalex.org/W4229003128","https://openalex.org/W4284697810","https://openalex.org/W4313547604","https://openalex.org/W4321485607","https://openalex.org/W4385573211","https://openalex.org/W4385573657","https://openalex.org/W6768003788","https://openalex.org/W6783227185","https://openalex.org/W6783990618","https://openalex.org/W6790588633","https://openalex.org/W6802778448","https://openalex.org/W6803755678"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2056396287"],"abstract_inverted_index":{"Pre-trained":[0],"code":[1,10,55,97,164,177],"models":[2,165],"have":[3,174],"emerged":[4],"as":[5,23],"the":[6,17,29,35,64,67,83,102,117,123,142,154,167,176],"state-of-the-art":[7],"paradigm":[8,14],"for":[9,96],"search":[11,98],"tasks.":[12],"The":[13,38],"involves":[15],"pre-training":[16],"model":[18],"on":[19,34,63,159],"search-irrelevant":[20],"tasks":[21],"such":[22],"masked":[24],"language":[25],"modeling,":[26],"followed":[27],"by":[28],"fine-tuning":[30,40],"stage,":[31],"which":[32,81,151],"focuses":[33],"search-relevant":[36],"task.":[37],"typical":[39,68],"method":[41,139],"is":[42],"to":[43,48,121,140,146],"employ":[44],"a":[45,93,111,133],"dual-encoder":[46,69,118],"architecture":[47,70,95],"encode":[49],"semantic":[50],"embeddings":[51],"of":[52,85,104,125,144,169],"query":[53,78,105],"and":[54,57,79,106,119,127],"separately,":[56],"then":[58],"calculate":[59],"their":[60],"similarity":[61],"based":[62],"embeddings.":[65],"However,":[66],"falls":[71],"short":[72],"in":[73],"modeling":[74],"token-level":[75],"interactions":[76],"between":[77],"code,":[80],"limits":[82],"capabilities":[84],"model.":[86],"To":[87],"address":[88],"this":[89],"limitation,":[90],"we":[91,131],"introduce":[92,110],"cross-encoder":[94,120,145],"that":[99,115],"jointly":[100],"encodes":[101],"concatenation":[103],"code.":[107],"We":[108,173],"further":[109,152],"Retriever-Ranker":[112],"(RR)":[113],"framework":[114],"cascades":[116],"promote":[122],"efficiency":[124],"evaluation":[126],"online":[128],"serving.":[129],"Moreover,":[130],"present":[132],"ranking-based":[134],"hard":[135,148],"negative":[136,149],"sampling":[137],"(PS)":[138],"improve":[141],"ability":[143],"distinguish":[147],"codes,":[150],"enhances":[153],"cascaded":[155],"RR":[156],"framework.":[157],"Experiments":[158],"four":[160],"datasets":[161],"using":[162],"three":[163],"demonstrate":[166],"superiority":[168],"our":[170],"proposed":[171],"method.":[172],"made":[175],"available":[178],"at":[179],"https://github.com/DongHande/R2PS.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}