{"id":4880,"date":"2022-11-03T10:38:13","date_gmt":"2022-11-03T10:38:13","guid":{"rendered":"https:\/\/otus.ru\/journal\/?p=4880"},"modified":"2022-11-03T10:42:35","modified_gmt":"2022-11-03T10:42:35","slug":"nlp-segodnya-ot-istokov-do-transformerov","status":"publish","type":"post","link":"https:\/\/otus.ru\/journal\/nlp-segodnya-ot-istokov-do-transformerov\/","title":{"rendered":"NLP \u0441\u0435\u0433\u043e\u0434\u043d\u044f: \u043e\u0442 \u0438\u0441\u0442\u043e\u043a\u043e\u0432 \u0434\u043e \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u043e\u0432"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_61 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >\u0421\u043e\u0434\u0435\u0440\u0436\u0430\u043d\u0438\u0435<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/otus.ru\/journal\/nlp-segodnya-ot-istokov-do-transformerov\/#%D0%97%D0%B0%D0%BF%D0%B8%D1%81%D1%8C_%D0%BE%D1%82%D0%BA%D1%80%D1%8B%D1%82%D0%BE%D0%B3%D0%BE_%D1%83%D1%80%D0%BE%D0%BA%D0%B0_%D0%BE%D0%BD%D0%BB%D0%B0%D0%B9%D0%BD-%D0%BA%D1%83%D1%80%D1%81%D0%B0_%C2%ABMachine_Learning_Professional%C2%AB\" title=\"\u0417\u0430\u043f\u0438\u0441\u044c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u0433\u043e \u0443\u0440\u043e\u043a\u0430 \u043e\u043d\u043b\u0430\u0439\u043d-\u043a\u0443\u0440\u0441\u0430 &#171;Machine Learning. Professional&#171;\">\u0417\u0430\u043f\u0438\u0441\u044c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u0433\u043e \u0443\u0440\u043e\u043a\u0430 \u043e\u043d\u043b\u0430\u0439\u043d-\u043a\u0443\u0440\u0441\u0430 &#171;Machine Learning. Professional&#171;<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/otus.ru\/journal\/nlp-segodnya-ot-istokov-do-transformerov\/#%D0%A1%D0%BC%D0%BE%D1%82%D1%80%D0%B5%D1%82%D1%8C_%D0%B7%D0%B0%D0%BF%D0%B8%D1%81%D0%B8_%D0%B4%D1%80%D1%83%D0%B3%D0%B8%D1%85_%D0%B2%D0%B5%D0%B1%D0%B8%D0%BD%D0%B0%D1%80%D0%BE%D0%B2\" title=\"\u0421\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0437\u0430\u043f\u0438\u0441\u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0432\u0435\u0431\u0438\u043d\u0430\u0440\u043e\u0432:\">\u0421\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0437\u0430\u043f\u0438\u0441\u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0432\u0435\u0431\u0438\u043d\u0430\u0440\u043e\u0432:<\/a><ul class='ez-toc-list-level-5' ><li class='ez-toc-heading-level-5'><ul class='ez-toc-list-level-5' ><li class='ez-toc-heading-level-5'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/otus.ru\/journal\/nlp-segodnya-ot-istokov-do-transformerov\/#Out_liar_%D0%9C%D0%B5%D1%82%D0%BE%D0%B4%D1%8B_%D0%B4%D0%B5%D1%82%D0%B5%D0%BA%D1%86%D0%B8%D0%B8_%D0%B0%D0%BD%D0%BE%D0%BC%D0%B0%D0%BB%D0%B8%D0%B9_%D0%B2_%D0%B4%D0%B0%D0%BD%D0%BD%D1%8B%D1%85\" title=\"Out liar! \u041c\u0435\u0442\u043e\u0434\u044b \u0434\u0435\u0442\u0435\u043a\u0446\u0438\u0438 \u0430\u043d\u043e\u043c\u0430\u043b\u0438\u0439 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445\">Out liar! \u041c\u0435\u0442\u043e\u0434\u044b \u0434\u0435\u0442\u0435\u043a\u0446\u0438\u0438 \u0430\u043d\u043e\u043c\u0430\u043b\u0438\u0439 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445<\/a><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%D0%97%D0%B0%D0%BF%D0%B8%D1%81%D1%8C_%D0%BE%D1%82%D0%BA%D1%80%D1%8B%D1%82%D0%BE%D0%B3%D0%BE_%D1%83%D1%80%D0%BE%D0%BA%D0%B0_%D0%BE%D0%BD%D0%BB%D0%B0%D0%B9%D0%BD-%D0%BA%D1%83%D1%80%D1%81%D0%B0_%C2%ABMachine_Learning_Professional%C2%AB\"><\/span>\u0417\u0430\u043f\u0438\u0441\u044c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u0433\u043e \u0443\u0440\u043e\u043a\u0430 \u043e\u043d\u043b\u0430\u0439\u043d-\u043a\u0443\u0440\u0441\u0430 <a href=\"https:\/\/otus.ru\/lessons\/machinelearning\/?utm_source=oj&amp;utm_medium=affilate&amp;utm_campaign=ml&amp;mxm=[[hash_metrika]]&amp;relogin=True&amp;token=[[token]]\" target=\"_blank\" rel=\"noopener\" title=\"\">&#171;<strong>Machine Learning. Professional<\/strong><\/a>&#171;<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"\u0414\u0435\u043c\u043e-\u0437\u0430\u043d\u044f\u0442\u0438\u0435 \u043a\u0443\u0440\u0441\u0430 \u00abMachine Learning. Professional\u00bb\" width=\"770\" height=\"433\" src=\"https:\/\/www.youtube.com\/embed\/geAKJkWAibg?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>Natural Language Processing (NLP) &#8212; \u044d\u0442\u043e \u043e\u0431\u043b\u0430\u0441\u0442\u044c ML, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0437\u0430\u043d\u0438\u043c\u0430\u0435\u0442\u0441\u044f \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0442\u0435\u043a\u0441\u0442\u043e\u0432. \u041d\u0430 \u044d\u0442\u043e\u043c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u043c \u0437\u0430\u043d\u044f\u0442\u0438\u0438 \u043f\u043e\u0433\u043e\u0432\u043e\u0440\u0438\u043b\u0438 \u043f\u0440\u043e \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b \u0438 \u043f\u043e\u0434\u0445\u043e\u0434\u044b, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0441\u0435\u0433\u043e\u0434\u043d\u044f \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u044e\u0442\u0441\u044f \u0432 NLP, \u043d\u0430\u0447\u0438\u043d\u0430\u044f \u043e\u0442 \u0441\u0430\u043c\u044b\u0445 \u043f\u0440\u043e\u0441\u0442\u044b\u0445 \u0438 \u0437\u0430\u043a\u0430\u043d\u0447\u0438\u0432\u0430\u044f \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u043d\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438, \u044f\u0432\u043b\u044f\u044e\u0449\u0438\u043c\u0438\u0441\u044f \u0441\u0442\u0430\u043d\u0434\u0430\u0440\u0442\u043e\u043c \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438.<\/p>\n\n\n\n<div class=\"wp-block-columns are-vertically-aligned-center is-layout-flex wp-container-core-columns-layout-1 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:15%\">\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"80\" height=\"80\" src=\"https:\/\/otus.ru\/journal\/wp-content\/uploads\/2022\/11\/Mariya_Tihonova_80x80.png\" alt=\"NLP \u0441\u0435\u0433\u043e\u0434\u043d\u044f: \u043e\u0442 \u0438\u0441\u0442\u043e\u043a\u043e\u0432 \u0434\u043e \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u043e\u0432\" class=\"wp-image-4881\"\/><\/figure><\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:2%\"><\/div>\n\n\n\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:55%\">\n<p class=\"has-text-align-left\" style=\"line-height:1.5\"><strong>\u0421\u043f\u0438\u043a\u0435\u0440: <strong>\u041c\u0430\u0440\u0438\u044f \u0422\u0438\u0445\u043e\u043d\u043e\u0432\u0430<\/strong><\/strong><\/p>\n\n\n\n<p class=\"has-text-align-left\" style=\"line-height:1.5\">Senior Data Scientist SberDevices, \u043f\u0440\u0435\u043f\u043e\u0434\u0430\u0432\u0430\u0442\u0435\u043b\u044c \u0432 \u0412\u0428\u042d \u0438 OTUS<\/p>\n<\/div>\n<\/div>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%D0%A1%D0%BC%D0%BE%D1%82%D1%80%D0%B5%D1%82%D1%8C_%D0%B7%D0%B0%D0%BF%D0%B8%D1%81%D0%B8_%D0%B4%D1%80%D1%83%D0%B3%D0%B8%D1%85_%D0%B2%D0%B5%D0%B1%D0%B8%D0%BD%D0%B0%D1%80%D0%BE%D0%B2\"><\/span>\u0421\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0437\u0430\u043f\u0438\u0441\u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0432\u0435\u0431\u0438\u043d\u0430\u0440\u043e\u0432:<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<h5 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Out_liar_%D0%9C%D0%B5%D1%82%D0%BE%D0%B4%D1%8B_%D0%B4%D0%B5%D1%82%D0%B5%D0%BA%D1%86%D0%B8%D0%B8_%D0%B0%D0%BD%D0%BE%D0%BC%D0%B0%D0%BB%D0%B8%D0%B9_%D0%B2_%D0%B4%D0%B0%D0%BD%D0%BD%D1%8B%D1%85\"><\/span><strong><a href=\"https:\/\/otus.ru\/lessons\/machinelearning\/?utm_source=oj&amp;utm_medium=affilate&amp;utm_campaign=ml&amp;mxm=[[hash_metrika]]&amp;relogin=True&amp;token=[[token]]#event-2232\" target=\"_blank\" rel=\"noopener\" title=\"\">Out liar! \u041c\u0435\u0442\u043e\u0434\u044b \u0434\u0435\u0442\u0435\u043a\u0446\u0438\u0438 \u0430\u043d\u043e\u043c\u0430\u043b\u0438\u0439 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445<\/a><\/strong><span class=\"ez-toc-section-end\"><\/span><\/h5>\n\n\n\n<p>\u0417\u0430\u0434\u0430\u0447\u0430 \u043f\u043e\u0438\u0441\u043a \u0430\u043d\u043e\u043c\u0430\u043b\u0438\u0439 \u0438 \u0432\u044b\u0431\u0440\u043e\u0441\u043e\u0432 (outliar detection) \u0432 \u0434\u0430\u043d\u043d\u044b\u0445 \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u043a\u0440\u0430\u0439\u043d\u0435 \u0432\u043e\u0441\u0442\u0440\u0435\u0431\u043e\u0432\u0430\u043d\u043d\u043e\u0439 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 ML. \u041d\u0430 \u0432\u0435\u0431\u0438\u043d\u0430\u0440\u0435 \u043e\u0431\u0441\u0443\u0434\u0438\u043b\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b \u0438 \u043f\u043e\u0434\u0445\u043e\u0434\u044b \u0434\u043b\u044f \u043f\u043e\u0438\u0441\u043a\u0430 \u0430\u043d\u043e\u043c\u0430\u043b\u0438\u0439 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438 \u043f\u0440\u0438\u043c\u0435\u043d\u0438\u043b\u0438 \u043d\u0430 \u043f\u0440\u0430\u043a\u0442\u0438\u043a\u0435 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0438\u0437 \u043d\u0438\u0445. <strong><a href=\"https:\/\/otus.ru\/lessons\/machinelearning\/?utm_source=oj&amp;utm_medium=affilate&amp;utm_campaign=ml&amp;mxm=[[hash_metrika]]&amp;relogin=True&amp;token=[[token]]#event-2232\" target=\"_blank\" rel=\"noopener\" title=\"\">\u0421\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0437\u0430\u043f\u0438\u0441\u044c<\/a><\/strong><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u0417\u0430\u043f\u0438\u0441\u044c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u0433\u043e \u0443\u0440\u043e\u043a\u0430 \u043e\u043d\u043b\u0430\u0439\u043d-\u043a\u0443\u0440\u0441\u0430 &#171;Machine Learning. Professional&#171; Natural Language Processing (NLP) &#8212; \u044d\u0442\u043e \u043e\u0431\u043b\u0430\u0441\u0442\u044c ML, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0437\u0430\u043d\u0438\u043c\u0430\u0435\u0442\u0441\u044f \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0442\u0435\u043a\u0441\u0442\u043e\u0432. \u041d\u0430 \u044d\u0442\u043e\u043c \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u043c \u0437\u0430\u043d\u044f\u0442\u0438\u0438 \u043f\u043e\u0433\u043e\u0432\u043e\u0440\u0438\u043b\u0438 \u043f\u0440\u043e \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b \u0438 \u043f\u043e\u0434\u0445\u043e\u0434\u044b, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0441\u0435\u0433\u043e\u0434\u043d\u044f \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u044e\u0442\u0441\u044f \u0432 NLP, \u043d\u0430\u0447\u0438\u043d\u0430\u044f \u043e\u0442 \u0441\u0430\u043c\u044b\u0445 \u043f\u0440\u043e\u0441\u0442\u044b\u0445 \u0438 \u0437\u0430\u043a\u0430\u043d\u0447\u0438\u0432\u0430\u044f \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u043d\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438, \u044f\u0432\u043b\u044f\u044e\u0449\u0438\u043c\u0438\u0441\u044f \u0441\u0442\u0430\u043d\u0434\u0430\u0440\u0442\u043e\u043c \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438. \u0421\u043f\u0438\u043a\u0435\u0440: \u041c\u0430\u0440\u0438\u044f \u0422\u0438\u0445\u043e\u043d\u043e\u0432\u0430 Senior Data Scientist SberDevices, \u043f\u0440\u0435\u043f\u043e\u0434\u0430\u0432\u0430\u0442\u0435\u043b\u044c \u0432<\/p>\n","protected":false},"author":10,"featured_media":4882,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"footnotes":""},"categories":[1],"tags":[201,169],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/posts\/4880"}],"collection":[{"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/comments?post=4880"}],"version-history":[{"count":1,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/posts\/4880\/revisions"}],"predecessor-version":[{"id":4885,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/posts\/4880\/revisions\/4885"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/media\/4882"}],"wp:attachment":[{"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/media?parent=4880"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/categories?post=4880"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/otus.ru\/journal\/wp-json\/wp\/v2\/tags?post=4880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}