{"id":"https://openalex.org/W4398785925","doi":"https://doi.org/10.1145/3639476.3639768","title":"Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?","display_name":"Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4398785925","doi":"https://doi.org/10.1145/3639476.3639768"},"language":"en","primary_location":{"id":"doi:10.1145/3639476.3639768","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639476.3639768","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639476.3639768","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results","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/10.1145/3639476.3639768","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030955183","display_name":"Alejandro Velasco","orcid":"https://orcid.org/0000-0002-4829-1017"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alejandro Velasco","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-4829-1017","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031468932","display_name":"David N. Palacio","orcid":"https://orcid.org/0000-0001-6166-7595"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David N. Palacio","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6166-7595","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, United States of America","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029623697","display_name":"Daniel Rodr\u00edguez-C\u00e1rdenas","orcid":"https://orcid.org/0000-0002-3238-1229"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Rodriguez-Cardenas","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3238-1229","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, United States of America","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041262116","display_name":"Denys Poshyvanyk","orcid":"https://orcid.org/0000-0002-5626-7586"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denys Poshyvanyk","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-5626-7586","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030955183"],"corresponding_institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"],"apc_list":null,"apc_paid":null,"fwci":2.984,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92163591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9904000163078308,"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/computer-science","display_name":"Computer science","score":0.8206536769866943},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.7623348832130432},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5524333715438843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.530831515789032},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.506294846534729},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49721816182136536},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.48790785670280457},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4771244525909424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46162277460098267},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4520034193992615},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.41518527269363403},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.062268584966659546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206536769866943},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.7623348832130432},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5524333715438843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.530831515789032},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.506294846534729},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49721816182136536},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.48790785670280457},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4771244525909424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46162277460098267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4520034193992615},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.41518527269363403},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.062268584966659546},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639476.3639768","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639476.3639768","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639476.3639768","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639476.3639768","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639476.3639768","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639476.3639768","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398785925.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1970018430","https://openalex.org/W1970607969","https://openalex.org/W2122076271","https://openalex.org/W2143861926","https://openalex.org/W2143891888","https://openalex.org/W2501364745","https://openalex.org/W2511803001","https://openalex.org/W2736762043","https://openalex.org/W2883359218","https://openalex.org/W2896457183","https://openalex.org/W2907705732","https://openalex.org/W2950368691","https://openalex.org/W2965373594","https://openalex.org/W3005628256","https://openalex.org/W3035010485","https://openalex.org/W3084812981","https://openalex.org/W3098605233","https://openalex.org/W3100026183","https://openalex.org/W3103170042","https://openalex.org/W3105247453","https://openalex.org/W3105903381","https://openalex.org/W3108032709","https://openalex.org/W3146720657","https://openalex.org/W3161997752","https://openalex.org/W3176740355","https://openalex.org/W3211801722","https://openalex.org/W4221167729","https://openalex.org/W4245415816","https://openalex.org/W4312090817","https://openalex.org/W4313549837","https://openalex.org/W4319792276","https://openalex.org/W4381713211","https://openalex.org/W4385572925","https://openalex.org/W4389544179","https://openalex.org/W4389633693","https://openalex.org/W4402665833"],"related_works":["https://openalex.org/W2077104824","https://openalex.org/W2536864162","https://openalex.org/W2613250302","https://openalex.org/W2390421503","https://openalex.org/W2387926336","https://openalex.org/W2143166528","https://openalex.org/W2364428493","https://openalex.org/W4400066978","https://openalex.org/W2773378563","https://openalex.org/W2137850935"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"the":[3,32,56,62,68,99],"limitations":[4],"of":[5,27,35,58,64],"evaluating":[6],"Masked":[7],"Language":[8],"Models":[9],"(MLMs)":[10],"in":[11,48,67],"code":[12],"completion":[13],"tasks.":[14],"We":[15,78,105],"highlight":[16],"that":[17,107],"relying":[18],"on":[19,72,83],"accuracy-based":[20],"measurements":[21],"may":[22],"lead":[23],"to":[24,54,112],"an":[25],"overestimation":[26],"models'":[28],"capabilities":[29],"by":[30],"neglecting":[31],"syntax":[33],"rules":[34],"programming":[36],"languages.":[37],"To":[38],"address":[39],"these":[40],"issues,":[41],"we":[42],"introduce":[43],"a":[44,80],"technique":[45],"called":[46],"SyntaxEval":[47,60],"which":[49],"Syntactic":[50],"Capabilities":[51],"are":[52],"used":[53],"enhance":[55],"evaluation":[57],"MLMs.":[59],"automates":[61],"process":[63],"masking":[65],"elements":[66],"model":[69],"input":[70],"based":[71],"their":[73],"Abstract":[74],"Syntax":[75],"Trees":[76],"(ASTs).":[77],"conducted":[79],"case":[81],"study":[82,110],"two":[84],"popular":[85],"MLMs":[86,108],"using":[87],"data":[88],"from":[89],"GitHub":[90],"repositories.":[91],"Our":[92],"results":[93],"showed":[94],"negative":[95],"causal":[96],"effects":[97],"between":[98],"node":[100],"types":[101],"and":[102],"MLMs'":[103],"accuracy.":[104],"conclude":[106],"under":[109],"fail":[111],"predict":[113],"some":[114],"syntactic":[115],"capabilities.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}