{"id":"https://openalex.org/W1994573369","doi":"https://doi.org/10.1145/2491411.2491458","title":"A statistical semantic language model for source code","display_name":"A statistical semantic language model for source code","publication_year":2013,"publication_date":"2013-08-18","ids":{"openalex":"https://openalex.org/W1994573369","doi":"https://doi.org/10.1145/2491411.2491458","mag":"1994573369"},"language":"en","primary_location":{"id":"doi:10.1145/2491411.2491458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491411.2491458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100642009","display_name":"Tung Nguyen","orcid":"https://orcid.org/0000-0003-4232-0566"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tung Thanh Nguyen","raw_affiliation_strings":["Iowa State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065748190","display_name":"Anh Tuan Nguyen","orcid":"https://orcid.org/0000-0002-9235-4759"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anh Tuan Nguyen","raw_affiliation_strings":["Iowa State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044339946","display_name":"Hoan Anh Nguyen","orcid":"https://orcid.org/0000-0002-6194-7930"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoan Anh Nguyen","raw_affiliation_strings":["Iowa State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089000736","display_name":"Tien N. Nguyen","orcid":"https://orcid.org/0009-0006-7962-6090"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tien N. Nguyen","raw_affiliation_strings":["Iowa State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":223,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"542"},"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":0.9970999956130981,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9957000017166138,"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":0.8358125686645508},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6545286178588867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5932827591896057},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.5639455914497375},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5602481961250305},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5346348285675049},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5323370695114136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44818755984306335},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4343514144420624},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4264480173587799},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4093971848487854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3454383611679077},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08610671758651733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358125686645508},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6545286178588867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5932827591896057},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.5639455914497375},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5602481961250305},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5346348285675049},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5323370695114136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44818755984306335},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4343514144420624},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4264480173587799},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4093971848487854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3454383611679077},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08610671758651733},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2491411.2491458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491411.2491458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W90447038","https://openalex.org/W1574901103","https://openalex.org/W1585991568","https://openalex.org/W1970607969","https://openalex.org/W1980450075","https://openalex.org/W1981109290","https://openalex.org/W1991945471","https://openalex.org/W2011458734","https://openalex.org/W2062068644","https://openalex.org/W2104210067","https://openalex.org/W2119414210","https://openalex.org/W2122076271","https://openalex.org/W2123044578","https://openalex.org/W2130344546","https://openalex.org/W2142403498","https://openalex.org/W2143960295","https://openalex.org/W2166597811","https://openalex.org/W2169952536"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2624072012","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W2132221452","https://openalex.org/W2008468404","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2081295016"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"successfully":[3],"applied":[4],"the":[5,37,50,58,85,99,106,146],"statistical":[6,69],"n-gram":[7,22,39,112],"language":[8,71],"model":[9,23,72],"to":[10,26,41,139],"show":[11],"that":[12],"source":[13,43,74],"code":[14,32,44,59,81,129],"exhibits":[15],"a":[16,54,67,127],"good":[17,28],"level":[18],"of":[19,57,87,119],"repetition.":[20],"The":[21],"is":[24,46,133],"shown":[25],"have":[27,140],"predictability":[29],"in":[30,53,102],"supporting":[31],"suggestion":[33,130],"and":[34,83],"completion.":[35],"However,":[36],"state-of-the-art":[38,147],"approach":[40],"capture":[42],"regularities/patterns":[45,86],"based":[47],"only":[48],"on":[49,123,136],"lexical":[51],"information":[52,79],"local":[55,100],"context":[56,101],"units.":[60],"To":[61],"improve":[62],"predictability,":[63],"we":[64,125],"introduce":[65],"SLAMC,":[66,124],"novel":[68],"semantic":[70,78,89,103],"for":[73],"code.":[75],"It":[76,97],"incorporates":[77],"into":[80,110],"tokens":[82],"models":[84],"such":[88],"annotations,":[90],"called":[91],"sememes,":[92],"rather":[93],"than":[94,145],"their":[95],"lexemes.":[96],"combines":[98],"n-grams":[104],"with":[105,116],"global":[107],"technical":[108],"concerns/functionality":[109],"an":[111],"topic":[113],"model,":[114],"together":[115],"pairwise":[117],"associations":[118],"program":[120],"elements.":[121],"Based":[122],"developed":[126],"new":[128],"method,":[131],"which":[132],"empirically":[134],"evaluated":[135],"several":[137],"projects":[138],"relatively":[141],"18-68%":[142],"higher":[143],"accuracy":[144],"approach.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}