{"id":"https://openalex.org/W4398239255","doi":"https://doi.org/10.1145/3639478.3643517","title":"Bringing Structure to Naturalness: On the Naturalness of ASTs","display_name":"Bringing Structure to Naturalness: On the Naturalness of ASTs","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4398239255","doi":"https://doi.org/10.1145/3639478.3643517"},"language":"en","primary_location":{"id":"doi:10.1145/3639478.3643517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3643517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3643517","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3643517","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051026501","display_name":"Profir-Petru P\u00e2r\u0163achi","orcid":"https://orcid.org/0000-0003-4940-6864"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Profir-Petru P\u00e2r\u021bachi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4940-6864","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066053285","display_name":"Mahito Sugiyama","orcid":"https://orcid.org/0000-0001-5907-9831"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mahito Sugiyama","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies, SOKENDAI, Kanagawwa, Japan","National Institute of Informatics, Tokyo, Japan The Graduate University for Advanced Studies, SOKENDAI, Kanagawwa, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5907-9831","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies, SOKENDAI, Kanagawwa, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan The Graduate University for Advanced Studies, SOKENDAI, Kanagawwa, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09023965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.995199978351593,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9872999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9006043672561646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259750604629517},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.6017704606056213},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5847744345664978},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.5283060073852539},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5062636137008667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4939311146736145},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.48880311846733093},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4879090487957001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4306561052799225},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.42521244287490845},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.36560267210006714}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9006043672561646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259750604629517},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.6017704606056213},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5847744345664978},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.5283060073852539},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5062636137008667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4939311146736145},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.48880311846733093},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4879090487957001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4306561052799225},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.42521244287490845},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.36560267210006714},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639478.3643517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3643517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3643517","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639478.3643517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3643517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3643517","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G2427697568","display_name":null,"funder_award_id":"JPMJCR22D3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G4854736940","display_name":null,"funder_award_id":"JP21H03503","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398239255.pdf","grobid_xml":"https://content.openalex.org/works/W4398239255.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1771830246","https://openalex.org/W2142403498","https://openalex.org/W2360967250","https://openalex.org/W2954274464","https://openalex.org/W2979271470","https://openalex.org/W3161743537"],"related_works":["https://openalex.org/W4308641625","https://openalex.org/W2077104824","https://openalex.org/W3176913510","https://openalex.org/W4389751695","https://openalex.org/W4310447811","https://openalex.org/W3012064729","https://openalex.org/W2388254906","https://openalex.org/W2955426500","https://openalex.org/W2786676889","https://openalex.org/W4213130063"],"abstract_inverted_index":{"Source":[0],"code":[1,13,26,35,54,56,71],"comes":[2],"in":[3],"different":[4],"shapes":[5],"and":[6,87,104],"forms.":[7],"Previous":[8],"research":[9,99,138],"has":[10,43],"already":[11],"shown":[12],"to":[14,47,153,163],"be":[15,28,84],"more":[16],"predictable":[17],"than":[18],"natural":[19],"language":[20,165],"at":[21],"the":[22,32,49,91,131,164],"token":[23,133],"level:":[24],"source":[25],"can":[27],"natural.":[29,77],"More":[30],"recently,":[31],"structure":[33],"of":[34,63,70],"---":[36,42],"either":[37],"as":[38,122,145],"graphs":[39],"or":[40,147],"trees":[41],"been":[44],"successfully":[45],"used":[46],"improve":[48],"state-of-the-art":[50,179],"on":[51,181],"numerous":[52],"tasks:":[53],"suggestion,":[55],"summarisation,":[57],"method":[58],"naming":[59,97],"etc.":[60],"This":[61],"body":[62],"work":[64],"implicitly":[65],"assumes":[66,101],"that":[67,80,100,157],"structured":[68],"representations":[69],"are":[72,124],"similarly":[73],"statistically":[74],"predictable,":[75],"i.e.":[76],"We":[78],"consider":[79],"this":[81,102],"view":[82],"should":[83],"made":[85],"explicit":[86],"propose":[88],"directly":[89],"studying":[90],"Structured":[92],"Naturalness":[93],"Hypothesis.":[94],"Beyond":[95],"just":[96],"existing":[98],"hypothesis":[103],"formulating":[105],"it,":[106],"we":[107,149,169],"also":[108],"provide":[109],"evidence":[110],"for":[111,118,177],"tree":[112,151],"representations:":[113],"TreeLSTM":[114],"models":[115,128,152],"over":[116],"ASTs":[117],"some":[119],"languages,":[120,143],"such":[121,144],"Ruby,":[123],"competitive":[125],"with":[126],"n-gram":[127],"while":[129],"handling":[130],"syntax":[132],"issue":[134],"highlighted":[135],"by":[136],"previous":[137],"'for":[139],"free'.":[140],"For":[141],"other":[142],"Java":[146],"Python,":[148],"find":[150],"perform":[154],"worse,":[155],"suggesting":[156],"downstream":[158],"task":[159],"improvement":[160],"is":[161],"uncorrelated":[162],"modelling":[166],"task.":[167],"Further,":[168],"show":[170],"how":[171],"one":[172],"may":[173],"use":[174],"naturalness":[175],"signals":[176],"near":[178],"results":[180],"just-in-time":[182],"defect":[183],"prediction":[184],"without":[185],"manual":[186],"feature":[187],"engineering":[188],"work.":[189]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
