{"id":"https://openalex.org/W4406255834","doi":"https://doi.org/10.18293/seke2024-094","title":"Build a Dataset of Query-Code Pairs Based on CodeSearchNet for Code Search (S)","display_name":"Build a Dataset of Query-Code Pairs Based on CodeSearchNet for Code Search (S)","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4406255834","doi":"https://doi.org/10.18293/seke2024-094"},"language":"en","primary_location":{"id":"doi:10.18293/seke2024-094","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2024-094","pdf_url":"https://doi.org/10.18293/seke2024-094","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2024-094","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102564692","display_name":"Yang Xu","orcid":"https://orcid.org/0009-0008-6473-8529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103263272","display_name":"Chao\u2010Wei Chen","orcid":"https://orcid.org/0009-0005-8864-8067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaowei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2024","issue":null,"first_page":"126","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9699000120162964,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8039554357528687},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6690107583999634},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5185502171516418},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5043312311172485},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.45971018075942993},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4365352392196655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4091620147228241},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1965087354183197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039554357528687},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6690107583999634},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5185502171516418},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5043312311172485},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.45971018075942993},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4365352392196655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4091620147228241},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1965087354183197},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2024-094","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2024-094","pdf_url":"https://doi.org/10.18293/seke2024-094","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2024-094","is_oa":true,"landing_page_url":"https://doi.org/10.18293/seke2024-094","pdf_url":"https://doi.org/10.18293/seke2024-094","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406255834.pdf","grobid_xml":"https://content.openalex.org/works/W4406255834.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W4256058599","https://openalex.org/W2572349046","https://openalex.org/W2901901036","https://openalex.org/W2026738364","https://openalex.org/W3125756434","https://openalex.org/W2146885082","https://openalex.org/W2538384344","https://openalex.org/W3049728138","https://openalex.org/W2184296057"],"abstract_inverted_index":{"CodeSearchNet":[0,55,73],"is":[1],"a":[2,64,75,104,111],"widely":[3],"used":[4],"dataset":[5,66],"of":[6,21,32,43,67,95,124,150,167,177],"commentcode":[7],"pairs":[8,23,45],"for":[9,56],"training":[10],"code":[11,14,57,127],"search":[12,15,58,128],"models.However,":[13],"models":[16],"trained":[17,130],"on":[18,88,131],"the":[19,33,79,84,93,122,125,141,148,151,157,162,175,178],"datasets":[20,42],"comment-code":[22],"usually":[24],"have":[25],"lower":[26,51],"performance":[27],"in":[28,48,52,165],"real-world":[29],"applications":[30],"because":[31],"semantic":[34,171],"gap":[35],"between":[36,98],"comments":[37],"and":[38,50,100,170],"real":[39,163],"queries.The":[40],"existing":[41],"query-code":[44,68,90],"are":[46],"smaller":[47],"size":[49],"quality":[53,149],"than":[54],"research.In":[59],"this":[60],"paper,":[61],"we":[62,102],"build":[63],"Python":[65],"pairs,":[69],"named":[70],"QCSN,":[71],"from":[72],"using":[74],"text":[76,80],"generator.We":[77],"train":[78],"generator":[81],"by":[82,134],"fine-tuning":[83],"pre-trained":[85],"model":[86,129],"PLBART":[87],"StaQC's":[89],"pairs.To":[91],"address":[92],"issue":[94],"domain":[96],"shift":[97],"StaQC":[99],"CodeSearchNet,":[101],"exploit":[103],"deep":[105,142],"adversarial":[106,143],"neural":[107,144],"network":[108,145],"that":[109,121,140,156],"trains":[110],"feature":[112],"extractor":[113],"to":[114],"extract":[115],"domain-invariant":[116],"features.The":[117],"experimental":[118],"results":[119],"show":[120],"MRR":[123],"typical":[126],"QCSN":[132],"improves":[133,147],"over":[135],"18.5%.The":[136],"ablation":[137],"study":[138],"indicates":[139],"module":[146],"generated":[152,158],"dataset.Further":[153],"evaluations":[154],"reveal":[155],"queries":[159,164],"closely":[160],"match":[161],"terms":[166],"lexical":[168],"overlap":[169],"similarity,":[172],"accurately":[173],"expressing":[174],"functionality":[176],"source":[179],"code.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}