{"id":"https://openalex.org/W4403383246","doi":"https://doi.org/10.3233/faia240733","title":"From Document to Program Embeddings: Can Distributional Hypothesis Really Be Used on Programming Languages?","display_name":"From Document to Program Embeddings: Can Distributional Hypothesis Really Be Used on Programming Languages?","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403383246","doi":"https://doi.org/10.3233/faia240733"},"language":"en","primary_location":{"id":"doi:10.3233/faia240733","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240733","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240733","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106475251","display_name":"Thibaut Martinet","orcid":"https://orcid.org/0000-0002-0170-9260"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thibaut Martinet","raw_affiliation_strings":["University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France"],"raw_orcid":"https://orcid.org/0000-0002-0170-9260","affiliations":[{"raw_affiliation_string":"University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035753375","display_name":"Guillaume Cleuziou","orcid":"https://orcid.org/0000-0002-2885-1152"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Cleuziou","raw_affiliation_strings":["University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France"],"raw_orcid":"https://orcid.org/0000-0002-2885-1152","affiliations":[{"raw_affiliation_string":"University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052645925","display_name":"Matthieu Exbrayat","orcid":"https://orcid.org/0000-0002-1740-4752"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Exbrayat","raw_affiliation_strings":["University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France"],"raw_orcid":"https://orcid.org/0000-0002-1740-4752","affiliations":[{"raw_affiliation_string":"University of Orl\u00e9ans, INSA-CVL, LIFO, EA 4022, F45067 Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077171510","display_name":"Fr\u00e9d\u00e9ric Flouvat","orcid":"https://orcid.org/0000-0001-7288-0498"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Flouvat","raw_affiliation_strings":["Aix Marseille Univ, CNRS, LIS, Marseille, France"],"raw_orcid":"https://orcid.org/0000-0001-7288-0498","affiliations":[{"raw_affiliation_string":"Aix Marseille Univ, CNRS, LIS, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I4210114274","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6858,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72916505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.916700005531311,"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"}},"topics":[{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.916700005531311,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6458976864814758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6193851828575134}],"concepts":[{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6458976864814758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6193851828575134}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia240733","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240733","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240733","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-04732269v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04732269","pdf_url":"https://hal.science/hal-04732269/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Artificial Intelligence (ECAI), Oct 2024, Saint-Jacques de Compostelle, Spain","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia240733","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240733","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240733","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403383246.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Programming":[0],"language":[1,48,157],"processing":[2],"is":[3,75,148,167],"a":[4,100,129,155,183,212],"field":[5,45,66],"of":[6,46,51,135,141,162,203,214,228,278],"increasing":[7],"interest,":[8],"as":[9,154,159],"more":[10,12],"and":[11,171,201,217,260,281],"models":[13,36,196],"become":[14],"available,":[15],"either":[16],"to":[17,22,67,70,79,97,106,118,131,169,172,174,211],"address":[18],"specific":[19,120],"tasks":[20],"or":[21],"acquire":[23],"general":[24],"knowledge":[25],"which":[26,98,191],"can":[27,103,221],"then":[28,127],"be":[29,85,104],"fine-tuned":[30],"on":[31,39,55,150,188,250,271],"downstream":[32],"tasks.":[33],"All":[34],"these":[35,136,274],"are":[37,252,277],"based":[38,149,187],"architectures":[40],"that":[41,81,219,234,247,267],"come":[42],"from":[43,59,64,90],"the":[44,56,119,133,139,142,151,163,195,198,204,208,268],"natural":[47],"processing,":[49],"most":[50],"them":[52],"being":[53],"built":[54],"distributional":[57,101,165,248],"hypothesis":[58,83,102,166],"linguistics.":[60],"Although":[61],"this":[62,82,93,110],"transition":[63],"one":[65],"another":[68],"appears":[69],"have":[71],"occurred":[72],"naturally,":[73],"it":[74],"not":[76],"so":[77],"obvious":[78],"claim":[80],"will":[84],"appropriate":[86],"for":[87],"extracting":[88],"semantics":[89,269],"programs.":[91],"In":[92],"paper,":[94],"we":[95,112,181,220,245,265],"investigate":[96],"extent":[99],"applied":[105],"code":[107],"embedding.":[108],"To":[109],"end,":[111],"first":[113],"formulate":[114],"various":[115],"hypotheses":[116,137,216,225,236,249,276],"adapted":[117],"information":[121,240],"contained":[122],"in":[123,226,254],"programming":[124],"languages.":[125],"We":[126,206],"provide":[128],"framework":[130,147,210],"evaluate":[132],"effectiveness":[134],"through":[138],"quality":[140],"resulting":[143],"embedding":[144],"spaces.":[145],"This":[146],"doc2vec":[152],"model":[153],"generic":[156],"model,":[158],"its":[160],"implementation":[161],"original":[164],"easy":[168],"understand":[170],"adapt":[173],"any":[175],"new":[176,184],"ones.":[177,243],"Among":[178],"other":[179],"tools,":[180],"propose":[182],"evaluation":[185],"method":[186],"program":[189],"analogies,":[190],"measures":[192],"how":[193],"well":[194],"capture":[197,237],"underlying":[199],"structure":[200],"meaning":[202],"code.":[205],"apply":[207],"proposed":[209],"set":[213],"(distributional)":[215],"show":[218],"rule":[222],"out":[223],"certain":[224],"favor":[227],"others.":[229],"Specifically,":[230],"our":[231],"study":[232],"indicates":[233],"instruction-based":[235],"less":[238],"semantic":[239],"than":[241],"token-based":[242],"Furthermore,":[244],"observe":[246],"tokens":[251],"effective":[253],"both":[255],"source":[256],"code,":[257],"execution":[258],"traces,":[259],"abstract":[261],"syntax":[262],"trees.":[263],"Additionally,":[264],"find":[266],"captured":[270],"programs":[272],"by":[273],"three":[275],"comparable":[279],"levels":[280],"natures.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
