A IBM apresentou a iniciativa CodeNet, voltada para fornecer aos pesquisadores um conjunto de dados que permite experimentar a aplica\u00e7\u00e3o de m\u00e9todos de aprendizado de m\u00e1quina para criar tradutores de uma linguagem de programa\u00e7\u00e3o para outra, al\u00e9m de geradores e analisadores de c\u00f3digo. O CodeNet inclui uma cole\u00e7\u00e3o de 14 milh\u00f5es de exemplos de c\u00f3digo que resolvem 4053 problemas de programa\u00e7\u00e3o t\u00edpicos. No total, a cole\u00e7\u00e3o conta com cerca de 500 milh\u00f5es de linhas de c\u00f3digo e abrange 55 linguagens de programa\u00e7\u00e3o, tanto linguagens modernas, como C++, Java, Python e Go, quanto obsoletas, incluindo COBOL, Pascal e FORTRAN. Os produtos do projeto s\u00e3o distribu\u00eddos sob a licen\u00e7a Apache 2.0, e os conjuntos de dados devem ser disponibilizados como dom\u00ednio p\u00fablico. <\/p>\n
Os exemplos s\u00e3o acompanhados de anota\u00e7\u00f5es e implementam algoritmos id\u00eanticos em diferentes linguagens de programa\u00e7\u00e3o. Espera-se que o conjunto proposto ajude no treinamento de sistemas de aprendizado de m\u00e1quina e no desenvolvimento de inova\u00e7\u00f5es nas \u00e1reas de tradu\u00e7\u00e3o e an\u00e1lise autom\u00e1tica de c\u00f3digo, assim como o banco de dados de imagens anotadas ImageNet ajudou no desenvolvimento de sistemas de reconhecimento de padr\u00f5es e vis\u00e3o computacional. Uma das principais fontes para a forma\u00e7\u00e3o da cole\u00e7\u00e3o s\u00e3o v\u00e1rias competi\u00e7\u00f5es de programa\u00e7\u00e3o. <\/p>\n
Ao contr\u00e1rio dos tradutores tradicionais, que s\u00e3o implementados com base em regras de transforma\u00e7\u00e3o, os sistemas de aprendizado de m\u00e1quina podem capturar e considerar o contexto de uso do c\u00f3digo. Ao converter de uma linguagem de programa\u00e7\u00e3o para outra, o contexto \u00e9 t\u00e3o importante quanto ao traduzir de uma l\u00edngua humana para outra. \u00c9 exatamente a falta de considera\u00e7\u00e3o do contexto que dificulta a transforma\u00e7\u00e3o de c\u00f3digo de linguagens obsoletas, como COBOL. <\/p>\n
A disponibilidade de uma grande base de implementa\u00e7\u00f5es de algoritmos em diversas linguagens ajudar\u00e1 na cria\u00e7\u00e3o de sistemas universais de aprendizado de m\u00e1quina, que, em vez de realizar uma tradu\u00e7\u00e3o direta entre linguagens espec\u00edficas, manipulam uma representa\u00e7\u00e3o de c\u00f3digo mais abstrata, independente das linguagens de programa\u00e7\u00e3o. Esse sistema pode ser usado como um tradutor, convertendo o c\u00f3digo enviado em qualquer uma das linguagens suportadas para sua representa\u00e7\u00e3o abstrata interna, a partir da qual pode ser gerado c\u00f3digo em v\u00e1rias linguagens. <\/p>\n
Al\u00e9m disso, o sistema poder\u00e1 realizar transforma\u00e7\u00f5es bidirecionais. Por exemplo, em bancos e institui\u00e7\u00f5es governamentais, ainda est\u00e3o em uso projetos na linguagem antiquada COBOL. Um tradutor baseado em um sistema de aprendizado de m\u00e1quina poder\u00e1 converter c\u00f3digo em COBOL para uma representa\u00e7\u00e3o em Java e, se necess\u00e1rio, traduzir um fragmento em Java de volta para c\u00f3digo em COBOL. <\/p>\n
Al\u00e9m da tradu\u00e7\u00e3o entre linguagens, s\u00e3o mencionadas \u00e1reas de aplica\u00e7\u00e3o do CodeNet, como a cria\u00e7\u00e3o de sistemas inteligentes de busca de c\u00f3digo e automa\u00e7\u00e3o na detec\u00e7\u00e3o de clones, bem como o desenvolvimento de otimizadores e sistemas de corre\u00e7\u00e3o autom\u00e1tica de c\u00f3digo. Em particular, os exemplos apresentados no CodeNet s\u00e3o acompanhados de metadados que descrevem os resultados de testes de desempenho, o tamanho resultante do programa, consumo de mem\u00f3ria e estado, permitindo distinguir c\u00f3digo correto de c\u00f3digo com erros (para diferenciar c\u00f3digo correto de incorreto, a cole\u00e7\u00e3o inclui intencionalmente exemplos com erros, cuja fra\u00e7\u00e3o \u00e9 de 29,5%). O sistema de aprendizado de m\u00e1quina pode levar em conta esses metadados para gerar o c\u00f3digo mais otimizado ou identificar regress\u00f5es no c\u00f3digo analisado (o sistema pode entender que o algoritmo no c\u00f3digo enviado n\u00e3o est\u00e1 implementado de forma otimizada ou cont\u00e9m erros). \u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f IBM \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0438\u043d\u0438\u0446\u0438\u0430\u0442\u0438\u0432\u0443 CodeNet, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u0443\u044e \u043d\u0430 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u043c \u043d\u0430\u0431\u043e\u0440\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0445 \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441 \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u0435\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0442\u0440\u0430\u043d\u0441\u043b\u044f\u0442\u043e\u0440\u043e\u0432 \u0438\u0437 \u043e\u0434\u043d\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u0432 \u0434\u0440\u0443\u0433\u043e\u0439, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u043e\u0440\u043e\u0432 \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0430\u0442\u043e\u0440\u043e\u0432 \u043a\u043e\u0434\u0430. CodeNet \u0432\u043a\u043b\u044e\u0447\u0430\u0435\u0442 \u043a\u043e\u043b\u043b\u0435\u043a\u0446\u0438\u044e \u0438\u0437 14 \u043c\u0438\u043b\u043b\u0438\u043e\u043d\u043e\u0432 \u043f\u0440\u0438\u043c\u0435\u0440\u043e\u0432 \u043a\u043e\u0434\u0430, \u0440\u0435\u0448\u0430\u044e\u0449\u0438\u0445 4053 \u0442\u0438\u043f\u043e\u0432\u044b\u0445 \u043f\u0440\u043e\u0431\u043b\u0435\u043c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f. \u0412 \u0441\u0443\u043c\u043c\u0435 \u043a\u043e\u043b\u043b\u0435\u043a\u0446\u0438\u044f \u043d\u0430\u0441\u0447\u0438\u0442\u044b\u0432\u0430\u0435\u0442 \u043e\u043a\u043e\u043b\u043e 500 \u043c\u043b\u043d \u0441\u0442\u0440\u043e\u043a \u043a\u043e\u0434\u0430 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-100141","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47A IBM lan\u00e7ou o CodeNet para sistemas de aprendizado de m\u00e1quina que traduzem e verificam c\u00f3digo | ProHoster","description":"A IBM apresentou a iniciativa CodeNet, voltada a fornecer aos pesquisadores um conjunto de dados que permite experimentar com m\u00e9todos de aprendizado de m\u00e1quina para criar tradutores de uma linguagem para outra.","canonical_url":"https:\/\/prohoster.info\/pt\/blog\/news\/ibm-otkryl-codenet-dlya-sistem-mashinnogo-obucheniya-transliruyushhih-i-proveryayushhih-kod","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"pt_PT","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47IBM \u043e\u0442\u043a\u0440\u044b\u043b CodeNet \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u0442\u0440\u0430\u043d\u0441\u043b\u0438\u0440\u0443\u044e\u0449\u0438\u0445 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u044e\u0449\u0438\u0445 \u043a\u043e\u0434 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f IBM \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0438\u043d\u0438\u0446\u0438\u0430\u0442\u0438\u0432\u0443 CodeNet, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u0443\u044e \u043d\u0430 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u043c \u043d\u0430\u0431\u043e\u0440\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0445 \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441 \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u0435\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0442\u0440\u0430\u043d\u0441\u043b\u044f\u0442\u043e\u0440\u043e\u0432 \u0438\u0437 \u043e\u0434\u043d\u043e\u0433\u043e.","og:url":"https:\/\/prohoster.info\/pt\/blog\/news\/ibm-otkryl-codenet-dlya-sistem-mashinnogo-obucheniya-transliruyushhih-i-proveryayushhih-kod","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2021-05-11T20:22:44+00:00","article:modified_time":"2021-05-11T20:22:44+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"100141","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-05-11 22:29:58","updated":"2022-09-28 07:50:50","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/100141","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/comments?post=100141"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/100141\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media?parent=100141"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/categories?post=100141"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/tags?post=100141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n
Fonte: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"