{"id":"https://openalex.org/W2944085062","doi":"https://doi.org/10.1145/3310273.3321560","title":"Capturing source code semantics via tree-based convolution over API-enhanced AST","display_name":"Capturing source code semantics via tree-based convolution over API-enhanced AST","publication_year":2019,"publication_date":"2019-04-30","ids":{"openalex":"https://openalex.org/W2944085062","doi":"https://doi.org/10.1145/3310273.3321560","mag":"2944085062"},"language":"en","primary_location":{"id":"doi:10.1145/3310273.3321560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310273.3321560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Computing Frontiers","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/A5100336402","display_name":"Long Chen","orcid":"https://orcid.org/0000-0002-5036-1539"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Long Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883632","display_name":"Wei Ye","orcid":"https://orcid.org/0009-0006-0568-9128"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ye","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101435571","display_name":"Shikun Zhang","orcid":"https://orcid.org/0000-0002-8576-2674"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100336402"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":4.0698,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94511283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9918000102043152,"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":0.8553558588027954},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.7419453859329224},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6960021257400513},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.692672848701477},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6418983936309814},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6102212071418762},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6036169528961182},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5572672486305237},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5387862920761108},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.49968433380126953},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4785374104976654},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.45243197679519653},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42676761746406555},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4234699010848999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39255058765411377},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37067335844039917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35102686285972595},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07891184091567993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553558588027954},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.7419453859329224},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6960021257400513},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.692672848701477},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6418983936309814},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6102212071418762},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6036169528961182},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5572672486305237},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5387862920761108},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.49968433380126953},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4785374104976654},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.45243197679519653},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42676761746406555},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4234699010848999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39255058765411377},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37067335844039917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35102686285972595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07891184091567993},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3310273.3321560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310273.3321560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1485912969","https://openalex.org/W1583837637","https://openalex.org/W1832693441","https://openalex.org/W2041190309","https://openalex.org/W2065053490","https://openalex.org/W2100060170","https://openalex.org/W2104246439","https://openalex.org/W2107878631","https://openalex.org/W2120615054","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2140609933","https://openalex.org/W2143960295","https://openalex.org/W2158439356","https://openalex.org/W2166278331","https://openalex.org/W2286236884","https://openalex.org/W2402619042","https://openalex.org/W2511803001","https://openalex.org/W2616911396","https://openalex.org/W2754629507","https://openalex.org/W2762844179","https://openalex.org/W2799201288","https://openalex.org/W2884276923","https://openalex.org/W2888557792","https://openalex.org/W2951861246","https://openalex.org/W2954552517","https://openalex.org/W4238623774","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W4389751695","https://openalex.org/W2077104824","https://openalex.org/W3176913510","https://openalex.org/W3138016835","https://openalex.org/W2536864162","https://openalex.org/W3197333277","https://openalex.org/W4389438938","https://openalex.org/W4282813445","https://openalex.org/W4200321676","https://openalex.org/W4317042421"],"abstract_inverted_index":{"When":[0],"deep":[1],"learning":[2],"meets":[3],"big":[4],"code,":[5],"a":[6,14],"key":[7],"question":[8],"is":[9],"how":[10],"to":[11,28,45],"efficiently":[12],"learn":[13],"distributed":[15],"representation":[16],"for":[17,93],"source":[18],"code":[19,94,97],"that":[20,59,67,89],"can":[21],"capture":[22],"its":[23],"semantics":[24,52],"effectively.":[25],"We":[26,85],"propose":[27,87],"use":[29],"tree-based":[30,69],"convolution":[31],"over":[32],"API-enhanced":[33],"AST.":[34],"To":[35],"demonstrate":[36],"the":[37],"effectiveness":[38],"of":[39,74],"our":[40,60,91],"approach,":[41],"we":[42],"apply":[43],"it":[44],"detect":[46],"semantic":[47],"clones---code":[48],"fragments":[49],"with":[50,71],"similar":[51],"but":[53],"dissimilar":[54],"syntax.":[55],"Experiment":[56],"results":[57],"show":[58],"approach":[61,66,92],"outperforms":[62],"an":[63,72],"existing":[64],"state-of-the-art":[65],"uses":[68],"LSTM,":[70],"increase":[73],"0.39":[75],"and":[76,82,96],"0.12":[77],"in":[78],"F1-score":[79],"on":[80],"OJClone":[81],"BigCloneBench":[83],"respectively.":[84],"further":[86],"architectures":[88],"incorporate":[90],"search":[95],"summarization.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}