{"id":"https://openalex.org/W4411630335","doi":"https://doi.org/10.18653/v1/2024.eacl-long.72","title":"Text-to-Code Generation with Modality-relative Pre-training","display_name":"Text-to-Code Generation with Modality-relative Pre-training","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630335","doi":"https://doi.org/10.18653/v1/2024.eacl-long.72"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.72","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.72","pdf_url":"https://aclanthology.org/2024.eacl-long.72.pdf","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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.72.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002307731","display_name":"Fenia Christopoulou","orcid":"https://orcid.org/0000-0001-5217-9848"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fenia Christopoulou","raw_affiliation_strings":["Huawei Noah's Ark Lab , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab , London , UK","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012683707","display_name":"Guchun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Guchun Zhang","raw_affiliation_strings":["Huawei Noah's Ark Lab , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab , London , UK","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039153096","display_name":"\u0393\u03b5\u03c1\u03ac\u03c3\u03b9\u03bc\u03bf\u03c2 \u039b\u03ac\u03bc\u03c0\u03bf\u03c5\u03c1\u03b1\u03c2","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gerasimos Lampouras","raw_affiliation_strings":["Huawei Noah's Ark Lab , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab , London , UK","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159102"],"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":"1194","last_page":"1208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9876999855041504,"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":0.9876999855041504,"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/T12031","display_name":"Speech and dialogue systems","score":0.9670000076293945,"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/T13629","display_name":"Text Readability and Simplification","score":0.9344000220298767,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7434694766998291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979045271873474},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5327568054199219},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43197867274284363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37350666522979736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37103337049484253},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2683867812156677}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7434694766998291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979045271873474},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5327568054199219},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43197867274284363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37350666522979736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37103337049484253},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2683867812156677},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.72","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.72","pdf_url":"https://aclanthology.org/2024.eacl-long.72.pdf","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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.72","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.72","pdf_url":"https://aclanthology.org/2024.eacl-long.72.pdf","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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630335.pdf","grobid_xml":"https://content.openalex.org/works/W4411630335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1,81],"language":[2,12,24,50,65,82],"models":[3,140],"have":[4,54],"recently":[5],"been":[6],"expanded":[7],"and":[8,32,76,95,105,133,141,147],"applied":[9],"to":[10,72,106],"programming":[11,34,49],"tasks":[13],"with":[14,115,125],"great":[15],"success,":[16],"often":[17,53],"through":[18],"further":[19,122],"pre-training":[20],"of":[21,41,110],"a":[22,148],"strictly-natural":[23],"model-where":[25],"training":[26,127],"sequences":[27],"typically":[28],"contain":[29],"both":[30,39],"natural":[31,64],"(linearised)":[33],"language.Such":[35],"approaches":[36],"effectively":[37],"map":[38],"modalities":[40,120],"the":[42,45,107,111],"sequence":[43,90],"into":[44],"same":[46],"embedding":[47,117],"space.However,":[48],"keywords":[51],"(e.g.\"while\")":[52],"very":[55],"strictly":[56],"defined":[57],"semantics.As":[58],"such,":[59],"transfer":[60],"learning":[61],"from":[62],"their":[63,73],"usage":[66],"may":[67],"not":[68],"necessarily":[69],"be":[70,93],"beneficial":[71],"code":[74],"application":[75],"vise":[77],"versa.Assuming":[78],"an":[79],"already":[80],"model,":[83],"in":[84],"this":[85],"work":[86],"we":[87],"investigate":[88],"how":[89],"tokens":[91],"can":[92],"adapted":[94],"represented":[96],"differently,":[97],"depending":[98],"on":[99,130],"which":[100],"modality":[101],"they":[102],"belong":[103],"to,":[104],"ultimate":[108],"benefit":[109],"downstream":[112],"task.We":[113],"experiment":[114],"separating":[116],"spaces":[118],"between":[119],"during":[121],"model":[123],"pretraining":[124],"modality-relative":[126],"objectives.We":[128],"focus":[129],"text-to-code":[131],"generation":[132],"observe":[134],"consistent":[135],"improvements":[136],"across":[137],"two":[138,142],"backbone":[139],"test":[143],"sets,":[144],"measuring":[145],"pass@k":[146],"novel":[149],"incremental":[150],"variation.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}