{"id":104737,"date":"2022-07-30T09:37:00","date_gmt":"2022-07-30T07:37:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0"},"modified":"2022-07-30T09:37:00","modified_gmt":"2022-07-30T07:37:00","slug":"vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hr\/blog\/news\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","title":{"rendered":"Izlazak sustava strojnog prevo\u0111enja OpenNMT 2.28.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Objavljen je izdanak sustava strojno prevo\u0111enja OpenNMT 0.28.0 (Open Neural Machine Translation), koji koristi metode strojnog u\u010denja. Za izgradnju neuronske mre\u017ee, projekt koristi mogu\u0107nosti biblioteke dubokog strojnog u\u010denja TensorFlow. Kod modula koji se razvijaju u okviru projekta OpenNMT napisan je na Pythonu i licenciran je pod MIT licencom. Gotovi modeli su pripremljeni za engleski, njema\u010dki i katalonski jezik, dok se za ostale jezike mo\u017ee samostalno izraditi model na temelju skupa podataka iz projekta OPUS (za u\u010denje sustava predaju se dvije datoteke - jedna s re\u010denicama na izvorom jeziku, a druga s kvalitetnim prijevodom tih re\u010denica na ciljni jezik). <\/p>\n

Projekt se razvija uz sudjelovanje tvrtke SYSTRAN, koja se specijalizira za stvaranje alata za strojno prevo\u0111enje, i grupe istra\u017eiva\u010da s Harvarda, koja razvija modele ljudskog jezika za sustave strojnog u\u010denja. Korisni\u010dko su\u010delje je maksimalno pojednostavljeno i zahtijeva samo navo\u0111enje ulazne datoteke s tekstom i datoteke za spremanje rezultata prevo\u0111enja. Sustav pro\u0161irenja omogu\u0107uje implementaciju dodatne funkcionalnosti na temelju OpenNMT, primjerice, autoreferenciranje, klasifikaciju tekstova i generiranje titlova. <\/p>\n

Primjena TensorFlow-a omogu\u0107uje kori\u0161tenje GPU-a (za ubrzavanje procesa u\u010denja neuronske mre\u017ee). Za pojednostavljenje distribucije proizvoda, projekt tako\u0111er razvija samodostatan oblik prevoditelja na C++ jeziku - CTranslate2, koji koristi prethodno trenirane modele bez ovisnosti o dodatnim komponentama. <\/p>\n

U novoj verziji dodan je parametar initial_learning_rate i implementirano je nekoliko novih argumenata (mha_bias i output_layer_bias) za pode\u0161avanje generatora modela Transformer. U ostalom se isti\u010du ispravci gre\u0161aka.
\n
Izvor: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u0430 OpenNMT 0.28.0 (Open Neural Machine Translation), \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0449\u0435\u0439 \u043c\u0435\u0442\u043e\u0434\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f. \u0414\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 \u043f\u0440\u043e\u0435\u043a\u0442 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442 \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0441\u0442\u0438 \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 \u0433\u043b\u0443\u0431\u0438\u043d\u043d\u043e\u0433\u043e \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f TensorFlow. \u041a\u043e\u0434 \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u044b\u0445 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u043c OpenNMT \u043c\u043e\u0434\u0443\u043b\u0435\u0439 \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python \u0438 \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u0435\u0442\u0441\u044f \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 MIT. \u0413\u043e\u0442\u043e\u0432\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u044b \u0434\u043b\u044f \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u0433\u043e, \u043d\u0435\u043c\u0435\u0446\u043a\u043e\u0433\u043e \u0438 \u043a\u0430\u0442\u0430\u043b\u0430\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u043e\u0432, \u0434\u043b\u044f \u043e\u0441\u0442\u0430\u043b\u044c\u043d\u044b\u0445 \u044f\u0437\u044b\u043a\u043e\u0432 \u043c\u043e\u0436\u043d\u043e \u0441\u0430\u043c\u043e\u0441\u0442\u043e\u044f\u0442\u0435\u043b\u044c\u043d\u043e […]<\/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-104737","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\udd47Izlazak sustava strojnog prevo\u0111enja OpenNMT 2.28.0 | ProHoster","description":"Objavljen je izlazak sustava strojnog prevo\u0111enja OpenNMT 0.28.0 (Open Neural Machine Translation), koji koristi metode strojnog u\u010denja.","canonical_url":"https:\/\/prohoster.info\/hr\/blog\/news\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hr_HR","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\udd47\u0412\u044b\u043f\u0443\u0441\u043a \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u0430 OpenNMT 2.28.0 | ProHoster","og:description":"\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u0430 OpenNMT 0.28.0 (Open Neural Machine Translation), \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0449\u0435\u0439 \u043c\u0435\u0442\u043e\u0434\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f.","og:url":"https:\/\/prohoster.info\/hr\/blog\/news\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","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":"2022-07-30T07:37:00+00:00","article:modified_time":"2022-07-30T07:37:00+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"104737","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":"default","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":"2022-07-30 07:38:11","updated":"2022-09-28 07:23:58","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts\/104737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/comments?post=104737"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts\/104737\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/media?parent=104737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/categories?post=104737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/tags?post=104737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}