{"id":"https://openalex.org/W4403536514","doi":"https://doi.org/10.1145/3691620.3695524","title":"Semi-Supervised Code Translation Overcoming the Scarcity of Parallel Code Data","display_name":"Semi-Supervised Code Translation Overcoming the Scarcity of Parallel Code Data","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403536514","doi":"https://doi.org/10.1145/3691620.3695524"},"language":"en","primary_location":{"id":"doi:10.1145/3691620.3695524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691620.3695524?download=true","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 39th IEEE/ACM International Conference on Automated Software Engineering","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/10.1145/3691620.3695524?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101813166","display_name":"Ming Zhu","orcid":"https://orcid.org/0000-0002-9128-076X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ming Zhu","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-9128-076X","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046709217","display_name":"Mohimenul Karim","orcid":"https://orcid.org/0000-0003-2808-7788"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohimenul Karim","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-2808-7788","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043962698","display_name":"Ismini Lourentzou","orcid":"https://orcid.org/0000-0002-1238-772X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ismini Lourentzou","raw_affiliation_strings":["University of Illinois Urbana - Champaign, Urbana - Champaign, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-1238-772X","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana - Champaign, Urbana - Champaign, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034366344","display_name":"Danfeng Yao","orcid":"https://orcid.org/0000-0001-8969-2792"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daphne Yao","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0001-8969-2792","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101813166"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75671089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1545","last_page":"1556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7892724275588989},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6624504327774048},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5967645645141602},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5096027851104736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4873705506324768},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46436119079589844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892724275588989},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6624504327774048},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5967645645141602},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5096027851104736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4873705506324768},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46436119079589844},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3691620.3695524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691620.3695524?download=true","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 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/121527","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/121527","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/59c79a52-05f0-45b9-a00c-fe39862e9965/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3691620.3695524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691620.3695524?download=true","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 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5468682457","display_name":null,"funder_award_id":"CNS-1929701","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403536514.pdf","grobid_xml":"https://content.openalex.org/works/W4403536514.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1972141422","https://openalex.org/W2074032109","https://openalex.org/W2247864914","https://openalex.org/W2963341956","https://openalex.org/W2981852735","https://openalex.org/W2985320478","https://openalex.org/W3001434439","https://openalex.org/W3034999214","https://openalex.org/W3098605233","https://openalex.org/W3170092793","https://openalex.org/W3198685994","https://openalex.org/W4288089799","https://openalex.org/W4361731444","https://openalex.org/W4362714579","https://openalex.org/W4385562549","https://openalex.org/W4387708155","https://openalex.org/W4389524561"],"related_works":["https://openalex.org/W1571141552","https://openalex.org/W4391636338","https://openalex.org/W4386067343","https://openalex.org/W4294250823","https://openalex.org/W2093086151","https://openalex.org/W55936454","https://openalex.org/W2095572632","https://openalex.org/W2944249426","https://openalex.org/W4294609170","https://openalex.org/W2056396287"],"abstract_inverted_index":{"Neural":[0],"code":[1,9,26,51,57,63,79,118,135,141,164,179,198],"translation":[2,33,52,165,199],"is":[3,21],"the":[4,18,22,30,88,95,126,144],"task":[5],"of":[6,17,24,32,90,121],"converting":[7],"source":[8,145],"from":[10,125,143],"one":[11],"programming":[12],"language":[13],"to":[14,35,75,86,148,192],"another.":[15],"One":[16],"main":[19],"challenges":[20],"scarcity":[23],"parallel":[25,56,78],"data,":[27,119],"which":[28],"hinders":[29],"ability":[31],"models":[34,169],"learn":[36],"accurate":[37],"cross-language":[38],"alignments.":[39],"In":[40],"this":[41,161],"paper,":[42],"we":[43],"introduce":[44],"MIRACLE,":[45],"a":[46,193],"semi-supervised":[47],"approach":[48],"that":[49,113,156,181],"improves":[50],"through":[53],"synthesizing":[54],"high-quality":[55],"data":[58,64,91],"and":[59,73,84,139,150,174],"curriculum":[60],"learning":[61],"on":[62,116],"with":[65,81,99,200],"ascending":[66],"alignment":[67,85],"levels.":[68],"MIRACLE":[69,177,188],"leverages":[70],"static":[71],"analysis":[72,111],"compilation":[74,149],"generate":[76],"synthetic":[77],"datasets":[80],"enhanced":[82],"quality":[83],"address":[87],"challenge":[89],"scarcity.":[92],"We":[93],"evaluate":[94],"proposed":[96],"method":[97,158],"along":[98],"strong":[100],"baselines":[101],"including":[102],"instruction-tuned":[103],"Large":[104],"Language":[105],"Models":[106],"(LLMs)":[107],"for":[108],"code.":[109],"Our":[110],"reveals":[112],"LLMs":[114,180],"pre-trained":[115],"open-source":[117],"regardless":[120],"their":[122],"size,":[123],"suffer":[124],"\"shallow":[127],"translation\"":[128],"problem.":[129],"This":[130],"issue":[131],"arises":[132],"when":[133],"translated":[134],"copies":[136],"keywords,":[137],"statements,":[138],"even":[140],"blocks":[142],"language,":[146],"leading":[147],"runtime":[151],"errors.":[152],"Extensive":[153],"experiments":[154],"demonstrate":[155],"our":[157],"significantly":[159],"mitigates":[160],"issue,":[162],"enhancing":[163],"performance":[166],"across":[167],"multiple":[168],"in":[170,186,196],"C++,":[171],"Java,":[172],"Python,":[173],"C.":[175],"Remarkably,":[176],"outperforms":[178],"are":[182],"ten":[183],"times":[184],"larger":[185],"size.":[187],"also":[189],"achieves":[190],"up":[191],"43%":[194],"improvement":[195],"C":[197],"fewer":[201],"than":[202],"150":[203],"annotated":[204],"examples.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}