{"id":"https://openalex.org/W3203911409","doi":"https://doi.org/10.1145/3465403","title":"CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words","display_name":"CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words","publication_year":2021,"publication_date":"2021-09-28","ids":{"openalex":"https://openalex.org/W3203911409","doi":"https://doi.org/10.1145/3465403","mag":"3203911409"},"language":"en","primary_location":{"id":"doi:10.1145/3465403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465403","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.14373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012001512","display_name":"Chao Liu","orcid":"https://orcid.org/0000-0001-5960-849X"},"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":"Chao Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["Huawei, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071834072","display_name":"Z. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwe Liu","raw_affiliation_strings":["Baidu Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Shanghai, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["Queen's University, Kingston, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114429788","display_name":"Shanping Li","orcid":"https://orcid.org/0000-0003-2615-9792"},"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":"Shanping Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9892,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95494248,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"31","issue":"1","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9988999962806702,"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":0.9986000061035156,"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":0.8847625255584717},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5162255764007568},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46692773699760437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43365800380706787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3544533848762512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8847625255584717},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5162255764007568},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46692773699760437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43365800380706787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3544533848762512}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3465403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465403","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2005.14373","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.14373","pdf_url":"https://arxiv.org/pdf/2005.14373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:ink.library.smu.edu.sg:sis_research-8651","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=8651&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3465403","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.14373","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.14373","pdf_url":"https://arxiv.org/pdf/2005.14373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W244339","https://openalex.org/W812573986","https://openalex.org/W1444168786","https://openalex.org/W1475493299","https://openalex.org/W1494726994","https://openalex.org/W1854214752","https://openalex.org/W1965636883","https://openalex.org/W1978896583","https://openalex.org/W1986601961","https://openalex.org/W1993786160","https://openalex.org/W2002072718","https://openalex.org/W2002219703","https://openalex.org/W2004247102","https://openalex.org/W2006291142","https://openalex.org/W2014755981","https://openalex.org/W2031289572","https://openalex.org/W2031874349","https://openalex.org/W2038721957","https://openalex.org/W2042803716","https://openalex.org/W2059556545","https://openalex.org/W2060055745","https://openalex.org/W2064675550","https://openalex.org/W2068632118","https://openalex.org/W2080579313","https://openalex.org/W2084887015","https://openalex.org/W2097001189","https://openalex.org/W2107376583","https://openalex.org/W2115350349","https://openalex.org/W2115733813","https://openalex.org/W2117642462","https://openalex.org/W2121265929","https://openalex.org/W2122401044","https://openalex.org/W2125980283","https://openalex.org/W2129384880","https://openalex.org/W2134092629","https://openalex.org/W2134829794","https://openalex.org/W2139374478","https://openalex.org/W2140952846","https://openalex.org/W2143960295","https://openalex.org/W2150775529","https://openalex.org/W2156448859","https://openalex.org/W2166481425","https://openalex.org/W2170460608","https://openalex.org/W2175297521","https://openalex.org/W2180107243","https://openalex.org/W2247374552","https://openalex.org/W2250861254","https://openalex.org/W2376637698","https://openalex.org/W2400994325","https://openalex.org/W2493916176","https://openalex.org/W2534712034","https://openalex.org/W2547932336","https://openalex.org/W2597820098","https://openalex.org/W2599156210","https://openalex.org/W2604794021","https://openalex.org/W2607180559","https://openalex.org/W2728599219","https://openalex.org/W2754109047","https://openalex.org/W2794601162","https://openalex.org/W2809365205","https://openalex.org/W2889423273","https://openalex.org/W2891617032","https://openalex.org/W2896457183","https://openalex.org/W2963879841","https://openalex.org/W2963921594","https://openalex.org/W2968179027","https://openalex.org/W2999343753","https://openalex.org/W3005855585","https://openalex.org/W3085514074","https://openalex.org/W3098605233","https://openalex.org/W3104874136","https://openalex.org/W3142518606","https://openalex.org/W3147574292","https://openalex.org/W3150708171","https://openalex.org/W4230473731","https://openalex.org/W4231326803","https://openalex.org/W4238080674","https://openalex.org/W4239358516","https://openalex.org/W4245995216","https://openalex.org/W4246531378","https://openalex.org/W4252080201","https://openalex.org/W4252684946","https://openalex.org/W4255375128","https://openalex.org/W4394638297"],"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/W4396696052"],"abstract_inverted_index":{"To":[0],"accelerate":[1,129],"software":[2],"development,":[3],"developers":[4],"frequently":[5],"search":[6,131,150,248],"and":[7,41,63,80,88,165,224,229,251,256,272,296],"reuse":[8],"existing":[9,246],"code":[10,29,61,173,182,217,284],"snippets":[11],"from":[12],"a":[13,168,190,197],"large-scale":[14,198],"codebase,":[15],"e.g.,":[16],"GitHub.":[17],"Over":[18],"the":[19,36,56,74,101,106,110,121,125,130,156,162,177,180,186,268,278],"years,":[20],"researchers":[21],"proposed":[22,94,233],"many":[23],"information":[24],"retrieval":[25],"(IR)-based":[26],"models":[27,274],"for":[28,139,216],"search,":[30,285],"but":[31],"they":[32],"fail":[33],"to":[34,128,142,175],"connect":[35],"semantic":[37],"gap":[38],"between":[39,58,84],"query":[40,87,115,140,153,295],"code.":[42,89,297],"An":[43],"early":[44],"successful":[45],"deep":[46],"learning":[47,55],"(DL)-based":[48],"model":[49,97,127,234],"DeepCS":[50,72,104],"solved":[51],"this":[52,91],"issue":[53],"by":[54,161,226,254],"relationship":[57],"pairs":[59],"of":[60,71,76,103,108,170,219,261,270,280],"methods":[62],"corresponding":[64],"natural":[65],"language":[66],"descriptions.":[67],"Two":[68],"major":[69],"advantages":[70,102,269],"are":[73],"capability":[75,107],"understanding":[77,109],"irrelevant/noisy":[78,144],"keywords":[79],"capturing":[81],"sequential":[82,111],"relationships":[83],"words":[85,141,154,188],"in":[86,113,124,179,189,259,293],"In":[90],"article,":[92],"we":[93],"an":[95,209,290],"IR-based":[96,126,271],"CodeMatcher":[98,135,207,243],"that":[99,158,206],"inherits":[100],"(i.e.,":[105],"semantics":[112],"important":[114,152,187,291],"words),":[116],"while":[117],"it":[118],"can":[119],"leverage":[120],"indexing":[122],"technique":[123],"response":[132],"time":[133],"substantially.":[134],"first":[136],"collects":[137],"metadata":[138],"identify":[143],"ones,":[145],"then":[146],"iteratively":[147],"performs":[148],"fuzzy":[149],"with":[151,200],"on":[155,196],"codebase":[157,199],"is":[159,235,275],"indexed":[160],"Elasticsearch":[163],"tool":[164],"finally":[166],"reranks":[167],"set":[169],"returned":[171],"candidate":[172,181],"according":[174],"how":[176],"tokens":[178],"snippet":[183],"sequentially":[184],"matched":[185],"query.":[191],"We":[192,263],"verified":[193],"its":[194],"effectiveness":[195],"~41K":[201],"repositories.":[202],"Experimental":[203],"results":[204],"showed":[205],"achieves":[208],"MRR":[210],"(a":[211],"widely":[212],"used":[213],"accuracy":[214],"measure":[215],"search)":[218,253],"0.60,":[220],"outperforming":[221],"DeepCS,":[222],"CodeHow,":[223],"UNIF":[225],"82%,":[227],"62%,":[228],"46%,":[230],"respectively.":[231],"Our":[232],"over":[236],"1.2K":[237],"times":[238],"faster":[239],"than":[240],"DeepCS.":[241],"Moreover,":[242],"outperforms":[244],"two":[245],"online":[247],"engines":[249],"(GitHub":[250],"Google":[252],"46%":[255],"33%,":[257],"respectively,":[258],"terms":[260],"MRR.":[262],"also":[264],"observed":[265],"that:":[266],"fusing":[267],"DL-based":[273],"promising;":[276],"improving":[277],"quality":[279],"method":[281,287],"naming":[282],"helps":[283],"since":[286],"name":[288],"plays":[289],"role":[292],"connecting":[294]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}