{"id":"https://openalex.org/W6983017160","doi":null,"title":"LEARNING PROGRAM EMBEDDING FROM UNLABELED SOURCE CODE","display_name":"LEARNING PROGRAM EMBEDDING FROM UNLABELED SOURCE CODE","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6983017160"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt92s294t8","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/92s294t8","pdf_url":"https://escholarship.org/content/qt92s294t8/qt92s294t8.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt92s294t8/qt92s294t8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ahmed, Toufique","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ahmed, Toufique","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","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/T10260","display_name":"Software Engineering Research","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":0.00039999998989515007,"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/T10533","display_name":"Teaching and Learning Programming","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/pre-trained-language-models","display_name":"pre-trained language models","score":0.6809999942779541},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.6489999890327454},{"id":"https://openalex.org/keywords/code-embeddings","display_name":"code embeddings","score":0.36899998784065247},{"id":"https://openalex.org/keywords/code-representation-learning","display_name":"code representation learning","score":0.4099999964237213},{"id":"https://openalex.org/keywords/code-correction","display_name":"code correction","score":0.5239999890327454},{"id":"https://openalex.org/keywords/binary-decompilation","display_name":"binary decompilation","score":0.9380000233650208},{"id":"https://openalex.org/keywords/multilingual-training","display_name":"multilingual training","score":0.8759999871253967},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.6639999747276306},{"id":"https://openalex.org/keywords/code-summarization","display_name":"code summarization","score":0.9800000190734863},{"id":"https://openalex.org/keywords/code-search","display_name":"code search","score":0.9929999709129333},{"id":"https://openalex.org/keywords/masked-language-modeling","display_name":"masked language modeling","score":0.5720000267028809},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.6399999856948853},{"id":"https://openalex.org/keywords/semantic-robustness","display_name":"semantic robustness","score":0.7039999961853027},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.7670000195503235},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.6380000114440918},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.8410000205039978},{"id":"https://openalex.org/keywords/software-engineering-tasks","display_name":"software engineering tasks","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262000203132629},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5863000154495239},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5178999900817871},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43650001287460327},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt92s294t8","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/92s294t8","pdf_url":"https://escholarship.org/content/qt92s294t8/qt92s294t8.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt92s294t8","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/92s294t8","pdf_url":"https://escholarship.org/content/qt92s294t8/qt92s294t8.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6983017160.pdf","grobid_xml":"https://content.openalex.org/works/W6983017160.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1816313093","https://openalex.org/W2133564696","https://openalex.org/W2574872930","https://openalex.org/W2785362762","https://openalex.org/W2809456172","https://openalex.org/W2896457183","https://openalex.org/W2905933322","https://openalex.org/W2908854766","https://openalex.org/W2936695845","https://openalex.org/W2945057371","https://openalex.org/W2949335953","https://openalex.org/W2958953787","https://openalex.org/W2965373594","https://openalex.org/W2971008324","https://openalex.org/W2981852735","https://openalex.org/W2996035354","https://openalex.org/W3008088841","https://openalex.org/W3016254928","https://openalex.org/W3030163527","https://openalex.org/W3040955294","https://openalex.org/W3046368065","https://openalex.org/W3081159607","https://openalex.org/W3126675481","https://openalex.org/W3137108338","https://openalex.org/W3153740501","https://openalex.org/W3159616622","https://openalex.org/W3166046636","https://openalex.org/W3169504754","https://openalex.org/W3173162544","https://openalex.org/W3177813494","https://openalex.org/W3182190622","https://openalex.org/W3183962691","https://openalex.org/W3184831477","https://openalex.org/W3185835445","https://openalex.org/W3186816466","https://openalex.org/W3194195934","https://openalex.org/W3195577433","https://openalex.org/W3198188208","https://openalex.org/W3211962263","https://openalex.org/W4226485558","https://openalex.org/W4281611258","https://openalex.org/W4283702402","https://openalex.org/W4284667247","https://openalex.org/W4298186941","https://openalex.org/W4321175641","https://openalex.org/W4382239980","https://openalex.org/W4384026634","https://openalex.org/W4385569771","https://openalex.org/W4385571689","https://openalex.org/W4385572925","https://openalex.org/W4389523793","https://openalex.org/W4394638297","https://openalex.org/W4394745253","https://openalex.org/W4407167185","https://openalex.org/W6950195680","https://openalex.org/W7133224126","https://openalex.org/W7133231369"],"related_works":["https://openalex.org/W2921999611","https://openalex.org/W3131945380","https://openalex.org/W4200633062","https://openalex.org/W3111914164","https://openalex.org/W4226463316","https://openalex.org/W3112383693","https://openalex.org/W4226326075","https://openalex.org/W4380687274","https://openalex.org/W4403593660","https://openalex.org/W4404783874"],"abstract_inverted_index":{"Machine-learning":[0],"models":[1,39,63,71,84,93,102,201,260,322,360],"can":[2,27,72,111,154,231,277,371],"reach":[3],"very":[4,48],"high":[5],"performance":[6,90,243,422,459],"with":[7,22,94,171,298,324,374],"supervised":[8,17,69,96],"training,":[9],"where":[10,346],"they":[11],"learn":[12,138,261],"from":[13,79,91,234],"labeled":[14],"data.":[15,81,97],"However,":[16,285,419],"training":[18,60,226,377],"requires":[19,64],"annotating":[20],"data":[21],"desired":[23],"output":[24],"labels,":[25],"which":[26,51,176],"be":[28,112,155,232,278],"a":[29,55,65,165,325,348,367,375,415,436],"difficult":[30],"and":[31,40,108,141,184,186,212,227,251,276,295,313,370,389,428],"time-consuming":[32],"task.":[33,167],"Meanwhile,":[34],"advancements":[35],"in":[36,202,414],"deep":[37],"learning":[38,78,270],"technology":[41],"have":[42,337,361],"made":[43],"it":[44,286],"possible":[45],"to":[46,87,105,196,237,300,316,328,405,409,449],"train":[47],"large":[49],"models,":[50,175],"was":[52],"not":[53],"feasible":[54],"few":[56,326,349,376],"years":[57],"ago.":[58],"Although":[59],"such":[61,117,208,215,282],"big":[62],"substantial":[66],"amount":[67],"of":[68,144,224,335,355,397,438],"data,":[70,107],"overcome":[73],"this":[74,150,444,461],"limitation":[75],"by":[76],"first":[77],"un-labeled":[80],"Pre-trained":[82],"language":[83,200,236,321],"enable":[85],"us":[86],"achieve":[88],"state-of-the-art":[89,458],"large-scale":[92],"limited":[95],"During":[98],"the":[99,136,142,145,152,222,241,263,290,309,353,364,395,398,403,407,420,426],"pre-training":[100,264],"stage,":[101],"are":[103,177,188,341,357],"exposed":[104],"unlabeled":[106],"their":[109],"weights":[110],"adjusted":[113],"using":[114,280],"self-supervised":[115],"tasks":[116,134,181,281,433],"as":[118,209,216,283],"filling":[119],"masks":[120],"or":[121,128,158,379],"spans,":[122],"de-":[123],"noising":[124],"artificially":[125],"induced":[126],"noises,":[127],"simple":[129,180],"auto-regressive":[130],"token":[131,139],"generation.":[132],"These":[133,359],"help":[135],"model":[137,153,291,310,408],"distributions":[140],"context":[143],"programming":[146],"language.":[147],"After":[148],"acquiring":[149],"knowledge,":[151],"easily":[156],"fine-tuned":[157,189],"used":[159],"even":[160,373],"without":[161],"any":[162],"fine-tuning":[163,368],"for":[164,190,366,431,440,454],"specific":[166],"This":[168],"thesis":[169],"began":[170],"work":[172],"on":[173,179,244,333,425,460],"foundation":[174,259],"pre-trained":[178,199],"like":[182],"mask-filling":[183],"de-noising,":[185],"then":[187],"task-specific":[191],"applications.":[192],"We":[193,219,255],"show":[194],"how":[195,229,448],"effectively":[197],"apply":[198],"SE":[203],"tasks,":[204],"including":[205],"traditional":[206],"ones":[207,214],"code":[210,247,249,455],"correction":[211],"novel":[213],"decompiling":[217],"binaries.":[218],"also":[220,256],"investigate":[221],"effectiveness":[223],"multilingual":[225],"demonstrate":[228,447],"knowledge":[230],"transferred":[233],"one":[235],"another,":[238],"thereby":[239],"improving":[240],"model\u2019s":[242,421],"three":[245],"tasks:":[246],"summarization,":[248,456],"search,":[250],"method":[252],"name":[253],"prediction.":[254],"investigated":[257],"what":[258],"during":[262,387],"stage.":[265],"It":[266],"is":[267,273,287,296,314],"evident":[268],"that":[269,308,386],"syntactical":[271],"distribution":[272,294],"relatively":[274],"easier":[275],"done":[279],"MLM.":[284],"unclear":[288],"whether":[289],"learns":[292,311],"semantic":[293],"robust":[297,315],"respect":[299],"meaning-preserving":[301,317],"transformations.":[302],"In":[303,443],"our":[304],"work,":[305,445],"we":[306,392,400,446],"found":[307],"semantics":[312],"transformations.More":[318],"recently,":[319],"Large":[320],"(LLMs),":[323],"billion":[327,330],"540":[329],"parameters,":[331],"trained":[332],"billions":[334],"tokens,":[336],"become":[338,435],"available.":[339],"They":[340],"proficient":[342],"at":[343,352,381],"few-shot":[344,390],"learning,":[345,391],"just":[347,401],"examples":[350],"provided":[351],"time":[354],"querying":[356],"sufficient.":[358],"largely":[362],"eliminated":[363],"need":[365],"stage":[369],"perform":[372],"samples":[378],"none":[380],"all.":[382],"It\u2019s":[383],"worth":[384],"noting":[385],"zero-shot":[388],"don\u2019t":[393],"change":[394],"parameters":[396],"model;":[399],"use":[402],"prompt":[404,429],"divert":[406],"condition":[410],"its":[411],"text":[412],"generation":[413],"more":[416],"desirable":[417],"manner.":[418],"heavily":[423],"relies":[424],"prompt,":[427],"engineering":[430],"different":[432],"has":[434],"focus":[437],"attention":[439],"numerous":[441],"researchers.":[442],"automatically":[450],"semantically":[451],"augment":[452],"prompts":[453],"achieving":[457],"task.\\n":[462]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}