{"id":16576,"date":"2024-01-27T07:04:23","date_gmt":"2024-01-27T03:34:23","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/"},"modified":"2024-01-27T07:04:23","modified_gmt":"2024-01-27T03:34:23","slug":"%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/","title":{"rendered":"\u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc Word2Vec \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\"><p class=\"ez-toc-title\" style=\"cursor:inherit\">\u0633\u0631\u0641\u0635\u0644\u0647\u0627\u06cc \u0645\u0637\u0644\u0628<\/p>\n<\/div><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:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%85%d8%b9%d8%b1%d9%81%db%8c\" >\u0645\u0639\u0631\u0641\u06cc<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%b1%d9%88%db%8c%da%a9%d8%b1%d8%af%d9%87%d8%a7%db%8c_%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87\" >\u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%da%a9%db%8c%d8%b3%d9%87_%da%a9%d9%84%d9%85%d8%a7%d8%aa\" >\u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%b7%d8%b1%d8%ad_tf-idf\" >\u0637\u0631\u062d TF-IDF<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#word2vec\" >Word2Vec<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#word2vec_%d8%af%d8%b1_%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86_%d8%a8%d8%a7_%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87_gensim\" >Word2Vec \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%a7%db%8c%d8%ac%d8%a7%d8%af_corpus\" >\u0627\u06cc\u062c\u0627\u062f Corpus<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4\" >\u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%a7%db%8c%d8%ac%d8%a7%d8%af_%d9%85%d8%af%d9%84_word2vec\" >\u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 Word2Vec<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%aa%d8%ad%d9%84%db%8c%d9%84_%d9%85%d8%af%d9%84\" >\u062a\u062d\u0644\u06cc\u0644 \u0645\u062f\u0644<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/rasanegaar.com\/blog\/%d9%be%db%8c%d8%a7%d8%af%d9%87-%d8%b3%d8%a7%d8%b2%db%8c-word2vec-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-gensim-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%86%d8%aa%db%8c%d8%ac%d9%87\" >\u0646\u062a\u06cc\u062c\u0647<\/a><\/li><\/ul><\/nav><\/div>\n<span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 10<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span><p> <br \/>\n<\/p>\n<div><noscript><\/noscript><\/p>\n<h2 id=\"introduction\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%b9%d8%b1%d9%81%db%8c\"><\/span>\u0645\u0639\u0631\u0641\u06cc<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u062f\u0627\u0631\u0627\u06cc \u062a\u0648\u0627\u0646\u0627\u06cc\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0628\u0631\u0627\u06cc \u062f\u0631\u06a9 \u0622\u0646\u0686\u0647 \u062f\u06cc\u06af\u0631\u0627\u0646 \u0645\u06cc \u06af\u0648\u06cc\u0646\u062f \u0648 \u0622\u0646\u0686\u0647 \u062f\u0631 \u067e\u0627\u0633\u062e \u0628\u0647 \u0622\u0646 \u0645\u06cc \u06af\u0648\u06cc\u0646\u062f\u060c \u062f\u0627\u0631\u0646\u062f.  \u0627\u06cc\u0646 \u062a\u0648\u0627\u0646\u0627\u06cc\u06cc \u0628\u0627 \u062a\u0639\u0627\u0645\u0644 \u0645\u062f\u0627\u0648\u0645 \u0628\u0627 \u0627\u0641\u0631\u0627\u062f \u062f\u06cc\u06af\u0631 \u0648 \u062c\u0627\u0645\u0639\u0647 \u062f\u0631 \u0637\u0648\u0644 \u0633\u0627\u0644\u06cc\u0627\u0646 \u0645\u062a\u0645\u0627\u062f\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u062f.  \u0632\u0628\u0627\u0646 \u0646\u0642\u0634 \u0628\u0633\u06cc\u0627\u0631 \u0645\u0647\u0645\u06cc \u062f\u0631 \u0631\u0648\u0634 \u062a\u0639\u0627\u0645\u0644 \u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u062f\u0627\u0631\u062f.  \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u0628\u0631\u0627\u06cc \u062a\u0639\u0627\u0645\u0644 \u0627\u0632 \u0622\u0646\u0647\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u0646\u062f\u060c \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0646\u0627\u0645\u06cc\u062f\u0647 \u0645\u06cc \u0634\u0648\u0646\u062f.<\/p>\n<p>\u0642\u0648\u0627\u0639\u062f \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u0637\u0628\u06cc\u0639\u06cc \u0645\u062a\u0641\u0627\u0648\u062a \u0627\u0633\u062a.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u06cc\u06a9 \u0686\u06cc\u0632 \u0645\u0634\u062a\u0631\u06a9 \u062f\u0631 \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f: \u0627\u0646\u0639\u0637\u0627\u0641 \u067e\u0630\u06cc\u0631\u06cc \u0648 \u062a\u06a9\u0627\u0645\u0644.<\/p>\n<p>\u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0628\u0633\u06cc\u0627\u0631 \u0627\u0646\u0639\u0637\u0627\u0641 \u067e\u0630\u06cc\u0631 \u0647\u0633\u062a\u0646\u062f.  \u0641\u0631\u0636 \u06a9\u0646\u06cc\u062f \u0634\u0645\u0627 \u062f\u0631 \u062d\u0627\u0644 \u0631\u0627\u0646\u0646\u062f\u06af\u06cc \u0647\u0633\u062a\u06cc\u062f \u0648 \u062f\u0648\u0633\u062a\u062a\u0627\u0646 \u06cc\u06a9\u06cc \u0627\u0632 \u0627\u06cc\u0646 \u0633\u0647 \u062c\u0645\u0644\u0647 \u0631\u0627 \u0645\u06cc \u06af\u0648\u06cc\u062f: &#8220;\u0628\u06a9\u0634\u060c \u0645\u0627\u0634\u06cc\u0646 \u0631\u0627 \u0645\u062a\u0648\u0642\u0641 \u06a9\u0646&#8221;\u060c &#8220;\u0627\u06cc\u0633\u062a&#8221;.  \u0628\u0644\u0627\u0641\u0627\u0635\u0644\u0647 \u0645\u062a\u0648\u062c\u0647 \u0645\u06cc \u0634\u0648\u06cc\u062f \u06a9\u0647 \u0627\u0648 \u0627\u0632 \u0634\u0645\u0627 \u0645\u06cc \u062e\u0648\u0627\u0647\u062f \u0645\u0627\u0634\u06cc\u0646 \u0631\u0627 \u0645\u062a\u0648\u0642\u0641 \u06a9\u0646\u06cc\u062f.  \u0627\u06cc\u0646 \u0628\u0647 \u0627\u06cc\u0646 \u062f\u0644\u06cc\u0644 \u0627\u0633\u062a \u06a9\u0647 \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0628\u0633\u06cc\u0627\u0631 \u0627\u0646\u0639\u0637\u0627\u0641 \u067e\u0630\u06cc\u0631 \u0647\u0633\u062a\u0646\u062f.  \u0631\u0627\u0647 \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641\u06cc \u0628\u0631\u0627\u06cc \u06af\u0641\u062a\u0646 \u06cc\u06a9 \u0686\u06cc\u0632 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.<\/p>\n<p>\u06cc\u06a9\u06cc \u062f\u06cc\u06af\u0631 \u0627\u0632 \u062c\u0646\u0628\u0647 \u0647\u0627\u06cc \u0645\u0647\u0645 \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 \u0622\u0646\u0647\u0627 \u0628\u0647 \u0637\u0648\u0631 \u0645\u062f\u0627\u0648\u0645 \u062f\u0631 \u062d\u0627\u0644 \u062a\u06a9\u0627\u0645\u0644 \u0647\u0633\u062a\u0646\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0686\u0646\u062f \u0633\u0627\u0644 \u067e\u06cc\u0634 \u0647\u06cc\u0686 \u0627\u0635\u0637\u0644\u0627\u062d\u06cc \u0645\u0627\u0646\u0646\u062f &#8220;Google it&#8221; \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0634\u062a \u06a9\u0647 \u0628\u0647 \u062c\u0633\u062a\u062c\u0648\u06cc \u0686\u06cc\u0632\u06cc \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f \u0631\u0648\u06cc \u0645\u0648\u062a\u0648\u0631 \u062c\u0633\u062a\u062c\u0648\u06cc \u06af\u0648\u06af\u0644  \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0647\u0645\u06cc\u0634\u0647 \u062f\u0631 \u062d\u0627\u0644 \u062a\u06a9\u0627\u0645\u0644 \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>\u0628\u0631\u0639\u06a9\u0633\u060c \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc \u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631\u06cc \u0627\u0632 \u06cc\u06a9 \u0646\u062d\u0648 \u062f\u0642\u06cc\u0642 \u067e\u06cc\u0631\u0648\u06cc \u0645\u06cc \u06a9\u0646\u0646\u062f.  \u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u0628\u0647 \u06cc\u06a9 \u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631 \u0628\u06af\u0648\u06cc\u06cc\u062f print \u0686\u06cc\u0632\u06cc \u0631\u0648\u06cc \u0635\u0641\u062d\u0647 \u0646\u0645\u0627\u06cc\u0634\u060c \u062f\u0633\u062a\u0648\u0631 \u062e\u0627\u0635\u06cc \u0628\u0631\u0627\u06cc \u0622\u0646 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.  \u0648\u0638\u06cc\u0641\u0647 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631\u0647\u0627 \u0632\u0628\u0627\u0646 \u0627\u0646\u0633\u0627\u0646 \u0631\u0627 \u0628\u0647 \u0631\u0648\u0634\u06cc \u0645\u0634\u0627\u0628\u0647 \u0627\u0646\u0633\u0627\u0646 \u062f\u0631\u06a9 \u06a9\u0631\u062f\u0647 \u0648 \u062a\u0648\u0644\u06cc\u062f \u06a9\u0646\u0646\u062f.<\/p>\n<p>\u0627\u06cc\u0646 \u06cc\u06a9 \u06a9\u0627\u0631 \u0628\u0632\u0631\u06af \u0627\u0633\u062a \u0648 \u0645\u0648\u0627\u0646\u0639 \u0632\u06cc\u0627\u062f\u06cc \u062f\u0631 \u0622\u0646 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.  \u0627\u06cc\u0646 <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/www.youtube.com\/watch?v=NHtohvD7gxY\">\u0633\u062e\u0646\u0631\u0627\u0646\u06cc \u062a\u0635\u0648\u06cc\u0631\u06cc<\/a> \u0627\u0632 \u062f\u0627\u0646\u0634\u06af\u0627\u0647 \u0645\u06cc\u0634\u06cc\u06af\u0627\u0646 \u062a\u0648\u0636\u06cc\u062d \u0628\u0633\u06cc\u0627\u0631 \u062e\u0648\u0628\u06cc \u062f\u0631 \u0645\u0648\u0631\u062f \u0627\u06cc\u0646\u06a9\u0647 \u0686\u0631\u0627 NLP \u0628\u0633\u06cc\u0627\u0631 \u0633\u062e\u062a \u0627\u0633\u062a\u060c \u0627\u0631\u0627\u0626\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0645\u06cc \u067e\u0631\u062f\u0627\u0632\u06cc\u0645 <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/en.wikipedia.org\/wiki\/Word2vec\">Word2Vec<\/a> \u062a\u06a9\u0646\u06cc\u06a9 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u0628\u0631\u062f\u0627\u0631 \u06a9\u0644\u0645\u0627\u062a \u0628\u0627 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/radimrehurek.com\/gensim\/\">\u062c\u0646\u0633\u06cc\u0645<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0642\u0628\u0644 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0645\u0633\u062a\u0642\u06cc\u0645\u0627\u064b \u0628\u0647 \u0628\u062e\u0634 \u06a9\u062f\u0646\u0648\u06cc\u0633\u06cc \u0628\u067e\u0631\u062f\u0627\u0632\u06cc\u0645\u060c \u0627\u0628\u062a\u062f\u0627 \u0628\u0631\u062e\u06cc \u0627\u0632 \u0631\u0627\u06cc\u062c \u062a\u0631\u06cc\u0646 \u062a\u06a9\u0646\u06cc\u06a9 \u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0631\u0627 \u0628\u0647 \u0647\u0645\u0631\u0627\u0647 \u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 \u0622\u0646\u0647\u0627 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u0631\u0648\u0631 \u0645\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<h2 id=\"wordembeddingapproaches\"><span class=\"ez-toc-section\" id=\"%d8%b1%d9%88%db%8c%da%a9%d8%b1%d8%af%d9%87%d8%a7%db%8c_%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87\"><\/span>\u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u06cc\u06a9\u06cc \u0627\u0632 \u062f\u0644\u0627\u06cc\u0644\u06cc \u06a9\u0647 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc \u0645\u0634\u06a9\u0644\u06cc \u0628\u0631\u0627\u06cc \u062d\u0644 \u0622\u0646 \u0627\u0633\u062a \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 \u0628\u0631\u062e\u0644\u0627\u0641 \u0627\u0646\u0633\u0627\u0646 \u0647\u0627\u060c \u0631\u0627\u06cc\u0627\u0646\u0647 \u0647\u0627 \u0641\u0642\u0637 \u0645\u06cc \u062a\u0648\u0627\u0646\u0646\u062f \u0627\u0639\u062f\u0627\u062f \u0631\u0627 \u062f\u0631\u06a9 \u06a9\u0646\u0646\u062f.  \u0645\u0627 \u0628\u0627\u06cc\u062f \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062f\u0631 \u0642\u0627\u0644\u0628 \u0639\u062f\u062f\u06cc \u0646\u0634\u0627\u0646 \u062f\u0647\u06cc\u0645 \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0631\u0627\u06cc\u0627\u0646\u0647 \u0642\u0627\u0628\u0644 \u062f\u0631\u06a9 \u0628\u0627\u0634\u062f.  \u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0646\u0645\u0627\u06cc\u0634 \u0639\u062f\u062f\u06cc \u06a9\u0644\u0645\u0627\u062a \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f.<\/p>\n<p>\u0686\u0646\u062f\u06cc\u0646 \u0631\u0648\u0634 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u062f\u0631 \u062d\u0627\u0644 \u062d\u0627\u0636\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u0648 \u0647\u0645\u0647 \u0622\u0646\u0647\u0627 \u062c\u0648\u0627\u0646\u0628 \u0645\u062b\u0628\u062a \u0648 \u0645\u0646\u0641\u06cc \u062e\u0648\u062f \u0631\u0627 \u062f\u0627\u0631\u0646\u062f.  \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0647 \u0633\u0647 \u0645\u0648\u0631\u062f \u0627\u0632 \u0622\u0646\u0647\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u067e\u0631\u062f\u0627\u062e\u062a:<\/p>\n<ol>\n<li>\u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a<\/li>\n<li>\u0637\u0631\u062d TF-IDF<\/li>\n<li>Word2Vec<\/li>\n<\/ol>\n<h3 id=\"bagofwords\"><span class=\"ez-toc-section\" id=\"%da%a9%db%8c%d8%b3%d9%87_%da%a9%d9%84%d9%85%d8%a7%d8%aa\"><\/span>\u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u06cc\u06a9\u06cc \u0627\u0632 \u0633\u0627\u062f\u0647 \u062a\u0631\u06cc\u0646 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a.  \u0645\u0631\u0627\u062d\u0644 \u0632\u06cc\u0631 \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u0633\u062a.<\/p>\n<p>\u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0645\u062b\u0627\u0644\u060c \u062a\u0639\u0628\u06cc\u0647\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0627\u06cc\u062c\u0627\u062f \u0634\u062f\u0647 \u062a\u0648\u0633\u0637 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f.  \u0641\u0631\u0636 \u06a9\u0646\u06cc\u062f \u0634\u0645\u0627 \u06cc\u06a9 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Text_corpus\">\u0645\u062c\u0645\u0648\u0639\u0647 \u0646\u0648\u0634\u062a\u0647 \u0647\u0627<\/a> \u0628\u0627 \u0633\u0647 \u062c\u0645\u0644\u0647<\/p>\n<ul>\n<li>S1 = \u0645\u0646 \u0639\u0627\u0634\u0642 \u0628\u0627\u0631\u0627\u0646 \u0647\u0633\u062a\u0645<\/li>\n<li>S2 = \u0628\u0627\u0631\u0627\u0646 \u0628\u0627\u0631\u0627\u0646 \u0627\u0632 \u0628\u06cc\u0646 \u0645\u06cc \u0631\u0648\u062f<\/li>\n<li>S3 = \u0645\u0646 \u062f\u0648\u0631 \u0647\u0633\u062a\u0645<\/li>\n<\/ul>\n<p>\u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u062c\u0645\u0644\u0627\u062a \u0628\u0627\u0644\u0627 \u0628\u0647 \u0646\u0645\u0627\u06cc\u0634 \u0647\u0627\u06cc \u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0647 \u0645\u062a\u0646\u0627\u0638\u0631 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a\u060c \u0628\u0627\u06cc\u062f \u0645\u0631\u0627\u062d\u0644 \u0632\u06cc\u0631 \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u062f\u0647\u06cc\u0645:<\/p>\n<ol>\n<li>\u06cc\u06a9 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f.  \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0641\u0648\u0642 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0627\u0631\u06cc\u0645: (\u0645\u0646\u060c \u0639\u0634\u0642\u060c \u0628\u0627\u0631\u0627\u0646\u060c \u0628\u0631\u0648\u060c \u062f\u0648\u0631\u060c \u0647\u0633\u062a\u0645)<\/li>\n<li>\u062c\u0645\u0644\u0647 \u0631\u0627 \u062a\u062c\u0632\u06cc\u0647 \u06a9\u0646  \u0628\u0631\u0627\u06cc \u0647\u0631 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u062c\u0645\u0644\u0647\u060c 1 \u0628\u0647 \u062c\u0627\u06cc \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f \u0648 \u0628\u0631\u0627\u06cc \u0647\u0645\u0647 \u06a9\u0644\u0645\u0627\u062a \u062f\u06cc\u06af\u0631\u06cc \u06a9\u0647 \u062f\u0631 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0631\u062f\u060c \u0635\u0641\u0631 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0646\u0645\u0627\u06cc\u0634 \u062c\u0645\u0644\u0647 S1 (\u0645\u0646 \u0639\u0627\u0634\u0642 \u0628\u0627\u0631\u0627\u0646 \u0647\u0633\u062a\u0645)\u060c \u0628\u0647 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u0627\u0633\u062a: (1\u060c 1\u060c 1\u060c 0\u060c 0\u060c 0).  \u0628\u0647 \u0637\u0648\u0631 \u0645\u0634\u0627\u0628\u0647 \u0628\u0631\u0627\u06cc S2 \u0648 S3\u060c \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc \u0627\u0632 \u0646\u0645\u0627\u06cc\u0634 \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628 (0\u060c 0\u060c 2\u060c 1\u060c 1\u060c 0) \u0648 (1\u060c 0\u060c 0\u060c 0\u060c 1\u060c 1) \u0647\u0633\u062a\u0646\u062f.<\/li>\n<\/ol>\n<p>\u062a\u0648\u062c\u0647 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u06a9\u0647 \u0628\u0631\u0627\u06cc S2 \u0645\u0627 2 \u0631\u0627 \u0628\u0647 \u062c\u0627\u06cc &#8220;\u0628\u0627\u0631\u0627\u0646&#8221; \u062f\u0631 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0627\u0636\u0627\u0641\u0647 \u06a9\u0631\u062f\u06cc\u0645.  \u0627\u06cc\u0646 \u0628\u0647 \u0627\u06cc\u0646 \u062f\u0644\u06cc\u0644 \u0627\u0633\u062a \u06a9\u0647 S2 \u062f\u0648 \u0628\u0627\u0631 \u062d\u0627\u0648\u06cc &#8220;\u0628\u0627\u0631\u0627\u0646&#8221; \u0627\u0633\u062a.<\/p>\n<h4 id=\"prosandconsofbagofwords\">\u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a<\/h4>\n<p>\u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0647\u0645 \u0645\u0632\u0627\u06cc\u0627 \u0648 \u0647\u0645 \u0645\u0639\u0627\u06cc\u0628 \u062f\u0627\u0631\u062f.  \u0645\u0632\u06cc\u062a \u0627\u0635\u0644\u06cc \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0628\u0647 \u062f\u0633\u062a \u0622\u0648\u0631\u062f\u0646 \u0646\u062a\u0627\u06cc\u062c \u062e\u0648\u0628 \u0628\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u0628\u0633\u06cc\u0627\u0631 \u0639\u0638\u06cc\u0645\u06cc \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a \u0646\u06cc\u0627\u0632 \u0646\u062f\u0627\u0631\u06cc\u062f.  \u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0645\u0627 \u06cc\u06a9 \u0645\u062f\u0644 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0628\u0633\u06cc\u0627\u0631 \u0627\u0628\u062a\u062f\u0627\u06cc\u06cc \u0628\u0627 \u0633\u0647 \u062c\u0645\u0644\u0647 \u0645\u06cc \u0633\u0627\u0632\u06cc\u0645.  \u0627\u0632 \u0646\u0638\u0631 \u0645\u062d\u0627\u0633\u0628\u0627\u062a\u06cc\u060c \u0645\u062f\u0644 \u06cc\u06a9 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u062e\u06cc\u0644\u06cc \u067e\u06cc\u0686\u06cc\u062f\u0647 \u0646\u06cc\u0633\u062a.<\/p>\n<p>\u06cc\u06a9 \u0627\u0634\u06a9\u0627\u0644 \u0639\u0645\u062f\u0647 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 \u0645\u0627 \u0646\u06cc\u0627\u0632 \u0628\u0647 \u0627\u06cc\u062c\u0627\u062f \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0628\u0632\u0631\u06af \u0628\u0627 \u0641\u0636\u0627\u0647\u0627\u06cc \u062e\u0627\u0644\u06cc \u062f\u0627\u0631\u06cc\u0645 \u062a\u0627 \u0639\u062f\u062f\u06cc (\u0645\u0627\u062a\u0631\u06cc\u0633 \u067e\u0631\u0627\u06a9\u0646\u062f\u0647) \u0631\u0627 \u0646\u0634\u0627\u0646 \u062f\u0647\u06cc\u0645 \u06a9\u0647 \u062d\u0627\u0641\u0638\u0647 \u0648 \u0641\u0636\u0627 \u0631\u0627 \u0645\u0635\u0631\u0641 \u0645\u06cc \u06a9\u0646\u062f.  \u062f\u0631 \u0645\u062b\u0627\u0644 \u0642\u0628\u0644\u06cc \u0641\u0642\u0637 3 \u062c\u0645\u0644\u0647 \u062f\u0627\u0634\u062a\u06cc\u0645.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0633\u0647 \u0635\u0641\u0631 \u0631\u0627 \u062f\u0631 \u0647\u0631 \u0628\u0631\u062f\u0627\u0631 \u0628\u0628\u06cc\u0646\u06cc\u062f.<\/p>\n<p>\u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc \u0628\u0627 \u0647\u0632\u0627\u0631\u0627\u0646 \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u062a\u0635\u0648\u0631 \u06a9\u0646\u06cc\u062f.  \u062f\u0631 \u0686\u0646\u06cc\u0646 \u062d\u0627\u0644\u062a\u06cc\u060c \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u06cc\u06a9 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0647\u0632\u0627\u0631\u0627\u0646 \u06a9\u0644\u0645\u0647 \u0628\u0627\u0634\u062f.  \u0627\u06af\u0631 \u06cc\u06a9 \u0633\u0646\u062f \u062d\u0627\u0648\u06cc 10\u066a \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0628\u0627\u0634\u062f\u060c \u0628\u0631\u062f\u0627\u0631 \u062c\u0627\u0633\u0627\u0632\u06cc \u0645\u0631\u0628\u0648\u0637\u0647 \u0647\u0645\u0686\u0646\u0627\u0646 \u062d\u0627\u0648\u06cc 90\u066a \u0635\u0641\u0631 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.<\/p>\n<p>\u06cc\u06a9\u06cc \u062f\u06cc\u06af\u0631 \u0627\u0632 \u0645\u0633\u0627\u0626\u0644 \u0645\u0647\u0645 \u0628\u0627 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 \u0647\u06cc\u0686 \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0632\u0645\u06cc\u0646\u0647 \u0627\u06cc \u0631\u0627 \u062d\u0641\u0638 \u0646\u0645\u06cc \u06a9\u0646\u062f.  \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628 \u0638\u0627\u0647\u0631 \u0634\u062f\u0646 \u06a9\u0644\u0645\u0627\u062a \u062f\u0631 \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u0627\u0647\u0645\u06cc\u062a\u06cc \u0646\u0645\u06cc \u062f\u0647\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0628\u0627 \u062c\u0645\u0644\u0627\u062a &#8220;\u0628\u0637\u0631\u06cc \u062f\u0631 \u0645\u0627\u0634\u06cc\u0646 \u0627\u0633\u062a&#8221; \u0648 &#8220;\u0645\u0627\u0634\u06cc\u0646 \u062f\u0631 \u0628\u0637\u0631\u06cc \u0627\u0633\u062a&#8221; \u0628\u0647 \u0637\u0648\u0631 \u0645\u0633\u0627\u0648\u06cc \u0631\u0641\u062a\u0627\u0631 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u062c\u0645\u0644\u0627\u062a \u06a9\u0627\u0645\u0644\u0627\u064b \u0645\u062a\u0641\u0627\u0648\u062a\u06cc \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>\u06cc\u06a9 \u0646\u0648\u0639 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u0627\u06cc \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a\u060c \u0645\u0639\u0631\u0648\u0641 \u0628\u0647 n-gram\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u062d\u0641\u0638 \u0631\u0627\u0628\u0637\u0647 \u0628\u06cc\u0646 \u06a9\u0644\u0645\u0627\u062a \u06a9\u0645\u06a9 \u06a9\u0646\u062f.  N-gram \u0628\u0647 \u062f\u0646\u0628\u0627\u0644\u0647 \u0627\u06cc \u0627\u0632 n \u06a9\u0644\u0645\u0647 \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c 2 \u06af\u0631\u0645 \u0628\u0631\u0627\u06cc \u062c\u0645\u0644\u0647 &#8220;\u0634\u0645\u0627 \u062e\u0648\u0634\u062d\u0627\u0644 \u0646\u06cc\u0633\u062a\u06cc\u062f&#8221;\u060c &#8220;\u0634\u0645\u0627 \u0647\u0633\u062a\u06cc\u062f&#8221;\u060c &#8220;\u0646\u06cc\u062f&#8221; \u0648 &#8220;\u062e\u0648\u0634\u062d\u0627\u0644 \u0646\u06cc\u0633\u062a\u06cc\u062f&#8221; \u0627\u0633\u062a.  \u0627\u06af\u0631\u0686\u0647 \u0631\u0648\u06cc\u06a9\u0631\u062f n-gram \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0631\u0648\u0627\u0628\u0637 \u0628\u06cc\u0646 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062b\u0628\u062a \u06a9\u0646\u062f\u060c \u0627\u0646\u062f\u0627\u0632\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627 \u0628\u0627 n-\u06af\u0631\u0645 \u0628\u0633\u06cc\u0627\u0631 \u0632\u06cc\u0627\u062f \u0628\u0647 \u0637\u0648\u0631 \u062a\u0635\u0627\u0639\u062f\u06cc \u0631\u0634\u062f \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<h3 id=\"tfidfscheme\"><span class=\"ez-toc-section\" id=\"%d8%b7%d8%b1%d8%ad_tf-idf\"><\/span>\u0637\u0631\u062d TF-IDF<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0637\u0631\u062d TF-IDF \u0646\u0648\u0639\u06cc \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u0644\u0645\u0627\u062a \u06a9\u06cc\u0633\u0647 \u0627\u06cc \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u0628\u0647 \u062c\u0627\u06cc \u0627\u0636\u0627\u0641\u0647 \u06a9\u0631\u062f\u0646 \u0635\u0641\u0631 \u0648 \u06cc\u06a9 \u062f\u0631 \u0628\u0631\u062f\u0627\u0631 \u062c\u0627\u0633\u0627\u0632\u06cc\u060c \u0627\u0639\u062f\u0627\u062f \u0634\u0646\u0627\u0648\u0631 \u0631\u0627 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u062f \u06a9\u0647 \u062d\u0627\u0648\u06cc \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0645\u0641\u06cc\u062f\u062a\u0631\u06cc \u062f\u0631 \u0645\u0642\u0627\u06cc\u0633\u0647 \u0628\u0627 \u0635\u0641\u0631 \u0648 \u06cc\u06a9 \u0647\u0633\u062a\u0646\u062f.  \u0627\u06cc\u062f\u0647 \u067e\u0634\u062a \u0637\u0631\u062d TF-IDF \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 \u06a9\u0644\u0645\u0627\u062a\u06cc \u06a9\u0647 \u062f\u0631 \u06cc\u06a9 \u0633\u0646\u062f \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u062f\u0627\u0631\u0646\u062f \u0648 \u062f\u0631 \u0633\u0627\u06cc\u0631 \u0627\u0633\u0646\u0627\u062f \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u06a9\u0645\u062a\u0631\u06cc \u062f\u0627\u0631\u0646\u062f\u060c \u0628\u0631\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0633\u06cc\u0627\u0631 \u0645\u0647\u0645 \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>TF-IDF \u062d\u0627\u0635\u0644\u0636\u0631\u0628 \u062f\u0648 \u0645\u0642\u062f\u0627\u0631 \u0627\u0633\u062a: \u0641\u0631\u06a9\u0627\u0646\u0633 \u0645\u062f\u062a (TF) \u0648 \u0641\u0631\u06a9\u0627\u0646\u0633 \u0633\u0646\u062f \u0645\u0639\u06a9\u0648\u0633 (IDF).<\/p>\n<p>\u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u0627\u0635\u0637\u0644\u0627\u062d \u0628\u0647 \u062a\u0639\u062f\u0627\u062f \u062f\u0641\u0639\u0627\u062a\u06cc \u06a9\u0647 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0633\u0646\u062f \u0638\u0627\u0647\u0631 \u0645\u06cc \u0634\u0648\u062f \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f \u0648 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0634\u0648\u062f:<\/p>\n<pre><code class=\"hljs\">Term frequence = (Number of Occurences of a word)\/(Total words in the document)\n<\/code><\/pre>\n<p>\u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0627\u06af\u0631 \u0628\u0647 \u062c\u0645\u0644\u0647 S1 \u0627\u0632 \u0628\u062e\u0634 \u0642\u0628\u0644\u06cc \u06cc\u0639\u0646\u06cc &#8220;\u0645\u0646 \u0639\u0627\u0634\u0642 \u0628\u0627\u0631\u0627\u0646 \u0647\u0633\u062a\u0645&#8221; \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u0645\u060c \u0647\u0631 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u062c\u0645\u0644\u0647 \u06cc\u06a9 \u0628\u0627\u0631 \u0631\u062e \u0645\u06cc \u062f\u0647\u062f \u0648 \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u062f\u0627\u0631\u0627\u06cc \u0641\u0631\u06a9\u0627\u0646\u0633 1 \u0627\u0633\u062a. \u0628\u0631\u0639\u06a9\u0633\u060c \u0628\u0631\u0627\u06cc S2 \u06cc\u0639\u0646\u06cc &#8220;\u0628\u0627\u0631\u0627\u0646 \u0628\u0627\u0631\u0627\u0646 \u0645\u06cc \u0631\u0648\u062f&#8221;\u060c \u0641\u0631\u0627\u0648\u0627\u0646\u06cc &#8220;\u0628\u0627\u0631\u0627\u0646&#8221; \u062f\u0648 \u0627\u0633\u062a \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0628\u0642\u06cc\u0647 \u06a9\u0644\u0645\u0627\u062a 1 \u0627\u0633\u062a.<\/p>\n<p>IDF \u0628\u0647 \u06af\u0632\u0627\u0631\u0634 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644 \u0627\u0633\u0646\u0627\u062f \u062a\u0642\u0633\u06cc\u0645 \u0628\u0631 \u062a\u0639\u062f\u0627\u062f \u0627\u0633\u0646\u0627\u062f\u06cc \u06a9\u0647 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0622\u0646\u0647\u0627 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f \u0648 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0634\u0648\u062f:<\/p>\n<pre><code class=\"hljs\">IDF(word) = Log((Total number of documents)\/(Number of documents containing the word))\n<\/code><\/pre>\n<p>\u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0645\u0642\u062f\u0627\u0631 IDF \u0628\u0631\u0627\u06cc \u06a9\u0644\u0645\u0647 &#8220;\u0628\u0627\u0631\u0627\u0646&#8221; 0.1760 \u0627\u0633\u062a\u060c \u0632\u06cc\u0631\u0627 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644 \u0627\u0633\u0646\u0627\u062f 3 \u0627\u0633\u062a \u0648 \u0628\u0627\u0631\u0627\u0646 \u062f\u0631 2 \u0645\u0648\u0631\u062f \u0627\u0632 \u0622\u0646\u0647\u0627 \u0638\u0627\u0647\u0631 \u0645\u06cc \u0634\u0648\u062f\u060c \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 <code>log(3\/2)<\/code> 0.1760 \u0627\u0633\u062a.  \u0627\u0632 \u0637\u0631\u0641 \u062f\u06cc\u06af\u0631\u060c \u0627\u06af\u0631 \u062f\u0631 \u062c\u0645\u0644\u0647 \u0627\u0648\u0644 \u0628\u0647 \u06a9\u0644\u0645\u0647 &#8220;\u0639\u0634\u0642&#8221; \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f\u060c \u062f\u0631 \u06cc\u06a9\u06cc \u0627\u0632 \u0633\u0647 \u0633\u0646\u062f \u0622\u0645\u062f\u0647 \u0627\u0633\u062a \u0648 \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u0645\u0642\u062f\u0627\u0631 IDF \u0622\u0646 \u0627\u0633\u062a. <code>log(3)<\/code>\u06a9\u0647 0.4771 \u0627\u0633\u062a.<\/p>\n<h4 id=\"prosandconsoftfidf\">\u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 TF-IDF<\/h4>\n<p>\u0627\u06af\u0631\u0686\u0647 TF-IDF \u067e\u06cc\u0634\u0631\u0641\u062a\u06cc \u0646\u0633\u0628\u062a \u0628\u0647 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0633\u0627\u062f\u0647 \u0627\u0633\u062a \u0648 \u0646\u062a\u0627\u06cc\u062c \u0628\u0647\u062a\u0631\u06cc \u0631\u0627 \u0628\u0631\u0627\u06cc \u06a9\u0627\u0631\u0647\u0627\u06cc \u0631\u0627\u06cc\u062c NLP \u0628\u0647 \u0627\u0631\u0645\u063a\u0627\u0646 \u0645\u06cc \u0622\u0648\u0631\u062f\u060c \u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 \u06a9\u0644\u06cc \u06cc\u06a9\u0633\u0627\u0646 \u0628\u0627\u0642\u06cc \u0645\u06cc \u0645\u0627\u0646\u0646\u062f.  \u0645\u0627 \u0647\u0646\u0648\u0632 \u0646\u06cc\u0627\u0632 \u0628\u0647 \u0627\u06cc\u062c\u0627\u062f \u06cc\u06a9 \u0645\u0627\u062a\u0631\u06cc\u0633 \u067e\u0631\u0627\u06a9\u0646\u062f\u0647 \u0628\u0632\u0631\u06af \u062f\u0627\u0631\u06cc\u0645\u060c \u06a9\u0647 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u062d\u0627\u0633\u0628\u0627\u062a \u0628\u0633\u06cc\u0627\u0631 \u0628\u06cc\u0634\u062a\u0631\u06cc \u0646\u0633\u0628\u062a \u0628\u0647 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0633\u0627\u062f\u0647 \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u062f.<\/p>\n<h3 id=\"word2vec\"><span class=\"ez-toc-section\" id=\"word2vec\"><\/span>Word2Vec<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><a target=\"_blank rel=\" href=\"https:\/\/en.wikipedia.org\/wiki\/Word2vec\" rel=\"noopener\">\u0631\u0648\u06cc\u06a9\u0631\u062f \u062c\u0627\u0633\u0627\u0632\u06cc Word2Vec \u06a9\u0647 \u062a\u0648\u0633\u0637 <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/research.fb.com\/people\/mikolov-tomas\/\">\u062a\u0648\u0645\u0627\u0633 \u0645\u06cc\u06a9\u0648\u0644\u0648\u0641<\/a>\u060c \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0636\u0639\u06cc\u062a \u0647\u0646\u0631 \u062f\u0631 \u0646\u0638\u0631 \u06af\u0631\u0641\u062a\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u0631\u0648\u06cc\u06a9\u0631\u062f Word2Vec \u0627\u0632 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0648 \u062a\u06a9\u0646\u06cc\u06a9\u200c\u0647\u0627\u06cc \u0645\u0628\u062a\u0646\u06cc \u0628\u0631 \u0634\u0628\u06a9\u0647\u200c\u0647\u0627\u06cc \u0639\u0635\u0628\u06cc \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0644\u0645\u0627\u062a \u0628\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u062a\u0646\u0627\u0638\u0631 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc\u200c\u06a9\u0646\u062f \u0628\u0647 \u06af\u0648\u0646\u0647\u200c\u0627\u06cc \u06a9\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u0634\u0627\u0628\u0647 \u0645\u0639\u0646\u0627\u06cc\u06cc \u062f\u0631 \u0641\u0636\u0627\u06cc N \u0628\u0639\u062f\u06cc \u0628\u0647 \u06cc\u06a9\u062f\u06cc\u06af\u0631 \u0646\u0632\u062f\u06cc\u06a9 \u0628\u0627\u0634\u0646\u062f\u060c \u062c\u0627\u06cc\u06cc \u06a9\u0647 N \u0628\u0647 \u0627\u0628\u0639\u0627\u062f \u0628\u0631\u062f\u0627\u0631 \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f.<\/p>\n<p>Word2Vec \u0646\u062a\u0627\u06cc\u062c \u0634\u06af\u0641\u062a \u0627\u0646\u06af\u06cc\u0632\u06cc \u0631\u0627 \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u062f\u0647\u062f.  \u062a\u0648\u0627\u0646\u0627\u06cc\u06cc Word2Vec \u0628\u0631\u0627\u06cc \u062d\u0641\u0638 \u0631\u0627\u0628\u0637\u0647 \u0645\u0639\u0646\u0627\u06cc\u06cc \u0628\u0627 \u06cc\u06a9 \u0645\u062b\u0627\u0644 \u06a9\u0644\u0627\u0633\u06cc\u06a9 \u0645\u0646\u0639\u06a9\u0633 \u0634\u062f\u0647 \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u0627\u06af\u0631 \u0628\u0631\u062f\u0627\u0631 \u06a9\u0644\u0645\u0647 &#8220;\u067e\u0627\u062f\u0634\u0627\u0647&#8221; \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u0648 \u0628\u0631\u062f\u0627\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u062a\u0648\u0633\u0637 \u06a9\u0644\u0645\u0647 &#8220;Man&#8221; \u0631\u0627 \u0627\u0632 &#8220;King&#8221; \u062d\u0630\u0641 \u06a9\u0646\u06cc\u062f \u0648 &#8220;Women&#8221; \u0631\u0627 \u0628\u0647 \u0622\u0646 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f\u060c \u0634\u0645\u0627 \u0628\u0631\u062f\u0627\u0631 \u0646\u0632\u062f\u06cc\u06a9 \u0628\u0647 \u0628\u0631\u062f\u0627\u0631 \u0645\u0644\u06a9\u0647 \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u06cc\u062f.  \u0627\u06cc\u0646 \u0631\u0627\u0628\u0637\u0647 \u0645\u0639\u0645\u0648\u0644\u0627\u064b \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0646\u0645\u0627\u06cc\u0634 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f:<\/p>\n<pre><code class=\"hljs\">King - Man + Women = Queen\n<\/code><\/pre>\n<p>\u0645\u062f\u0644 Word2Vec \u062f\u0631 \u062f\u0648 \u0646\u0648\u0639 \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u0634\u0648\u062f: \u0645\u062f\u0644 Skip Gram \u0648 Continuous Bag of Words Model (CBOW).<\/p>\n<p>\u062f\u0631 \u0645\u062f\u0644 Skip Gram\u060c \u06a9\u0644\u0645\u0627\u062a \u0632\u0645\u06cc\u0646\u0647 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06a9\u0644\u0645\u0647 \u067e\u0627\u06cc\u0647 \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0645\u06cc \u0634\u0648\u0646\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 \u062c\u0645\u0644\u0647 &#8220;I love to dance in the rain&#8221;\u060c \u0645\u062f\u0644 skip gram &#8220;\u0639\u0634\u0642&#8221; \u0648 &#8220;\u0631\u0642\u0635&#8221; \u0631\u0627 \u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 \u06a9\u0644\u0645\u0647 &#8220;to&#8221; \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<p>\u0628\u0631\u0639\u06a9\u0633\u060c \u0645\u062f\u0644 CBOW \u00ab\u0628\u0647\u00bb \u0631\u0627 \u067e\u06cc\u0634\u200c\u0628\u06cc\u0646\u06cc \u0645\u06cc\u200c\u06a9\u0646\u062f\u060c \u0627\u06af\u0631 \u06a9\u0644\u0645\u0627\u062a \u0645\u062a\u0646\u06cc \u00ab\u0639\u0634\u0642\u00bb \u0648 \u00ab\u0631\u0642\u0635\u00bb \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u0628\u0647 \u0645\u062f\u0644 \u062f\u0627\u062f\u0647 \u0634\u0648\u0646\u062f.  \u0645\u062f\u0644 \u0627\u06cc\u0646 \u0631\u0648\u0627\u0628\u0637 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0634\u0628\u06a9\u0647 \u0647\u0627\u06cc \u0639\u0635\u0628\u06cc \u0639\u0645\u06cc\u0642 \u06cc\u0627\u062f \u0645\u06cc \u06af\u06cc\u0631\u062f.<\/p>\n<h4 id=\"prosandconsofword2vec\">\u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 Word2Vec<\/h4>\n<p>Word2Vec \u062f\u0627\u0631\u0627\u06cc \u0686\u0646\u062f\u06cc\u0646 \u0645\u0632\u06cc\u062a \u0646\u0633\u0628\u062a \u0628\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u06a9\u0644\u0645\u0627\u062a \u0648 \u0637\u0631\u062d IF-IDF \u0627\u0633\u062a.  Word2Vec \u0645\u0639\u0646\u0627\u06cc \u0645\u0639\u0646\u0627\u06cc\u06cc \u06a9\u0644\u0645\u0627\u062a \u0645\u062e\u062a\u0644\u0641 \u062f\u0631 \u06cc\u06a9 \u0633\u0646\u062f \u0631\u0627 \u062d\u0641\u0638 \u0645\u06cc \u06a9\u0646\u062f.  \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0632\u0645\u06cc\u0646\u0647 \u0627\u0632 \u0628\u06cc\u0646 \u0646\u0645\u06cc \u0631\u0648\u062f.  \u06cc\u06a9\u06cc \u062f\u06cc\u06af\u0631 \u0627\u0632 \u0645\u0632\u0627\u06cc\u0627\u06cc \u0628\u0632\u0631\u06af \u0631\u0648\u06cc\u06a9\u0631\u062f Word2Vec \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u0628\u0631\u062f\u0627\u0631 \u062c\u0627\u0633\u0627\u0632\u06cc \u0628\u0633\u06cc\u0627\u0631 \u06a9\u0648\u0686\u06a9 \u0627\u0633\u062a.  \u0647\u0631 \u0628\u0639\u062f \u062f\u0631 \u0628\u0631\u062f\u0627\u0631 \u062c\u0627\u0633\u0627\u0632\u06cc \u062d\u0627\u0648\u06cc \u0627\u0637\u0644\u0627\u0639\u0627\u062a\u06cc \u062f\u0631 \u0645\u0648\u0631\u062f \u06cc\u06a9 \u062c\u0646\u0628\u0647 \u0627\u0632 \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a.  \u0645\u0627 \u0628\u0631\u062e\u0644\u0627\u0641 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0648 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc TF-IDF \u0628\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u067e\u0631\u0627\u06a9\u0646\u062f\u0647 \u0639\u0638\u06cc\u0645 \u0646\u06cc\u0627\u0632 \u0646\u062f\u0627\u0631\u06cc\u0645.<\/p>\n<p><strong>\u062a\u0648\u062c\u0647 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f<\/strong>: \u062c\u0632\u0626\u06cc\u0627\u062a \u0631\u06cc\u0627\u0636\u06cc \u0631\u0648\u0634 \u06a9\u0627\u0631 Word2Vec \u0634\u0627\u0645\u0644 \u062a\u0648\u0636\u06cc\u062d\u06cc \u062f\u0631 \u0645\u0648\u0631\u062f \u0634\u0628\u06a9\u0647 \u0647\u0627\u06cc \u0639\u0635\u0628\u06cc \u0648 \u0627\u062d\u062a\u0645\u0627\u0644 \u0646\u0631\u0645 \u0627\u0641\u0632\u0627\u0631 \u0645\u06a9\u0633 \u0645\u06cc \u0628\u0627\u0634\u062f \u06a9\u0647 \u0627\u0632 \u062d\u0648\u0635\u0644\u0647 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u062e\u0627\u0631\u062c \u0627\u0633\u062a.  \u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u067e\u0627\u06cc\u0647 \u0647\u0627\u06cc \u0631\u06cc\u0627\u0636\u06cc Word2Vec \u0631\u0627 \u062f\u0631\u06a9 \u06a9\u0646\u06cc\u062f\u060c \u0644\u0637\u0641\u0627\u064b \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u0628\u062e\u0648\u0627\u0646\u06cc\u062f: <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/arxiv.org\/abs\/1301.3781\">https:\/\/arxiv.org\/abs\/1301.3781<\/a><\/p>\n<h2 id=\"word2vecinpythonwithgensimlibrary\"><span class=\"ez-toc-section\" id=\"word2vec_%d8%af%d8%b1_%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86_%d8%a8%d8%a7_%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87_gensim\"><\/span>Word2Vec \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0642\u0633\u0645\u062a \u0645\u062f\u0644 Word2Vec \u0631\u0627 \u0628\u0627 \u06a9\u0645\u06a9 \u067e\u0627\u06cc\u062a\u0648\u0646 \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0645\u06cc \u06a9\u0646\u06cc\u0645 <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/radimrehurek.com\/gensim\/\">\u062c\u0646\u0633\u06cc\u0645<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647  \u0627\u06cc\u0646 \u0645\u0631\u0627\u062d\u0644 \u0631\u0627 \u062f\u0646\u0628\u0627\u0644 \u06a9\u0646\u06cc\u062f:<\/p>\n<h3 id=\"creatingcorpus\"><span class=\"ez-toc-section\" id=\"%d8%a7%db%8c%d8%ac%d8%a7%d8%af_corpus\"><\/span>\u0627\u06cc\u062c\u0627\u062f Corpus<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0642\u0628\u0644\u0627\u064b \u0628\u062d\u062b \u06a9\u0631\u062f\u06cc\u0645 \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u06cc\u06a9 \u0645\u062f\u0644 Word2Vec\u060c \u0628\u0647 \u06cc\u06a9 \u067e\u06cc\u06a9\u0631\u0647 \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u0645.  \u062f\u0631 \u0628\u0631\u0646\u0627\u0645\u0647 \u0647\u0627\u06cc \u06a9\u0627\u0631\u0628\u0631\u062f\u06cc \u0648\u0627\u0642\u0639\u06cc\u060c \u0645\u062f\u0644 \u0647\u0627\u06cc Word2Vec \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0645\u06cc\u0644\u06cc\u0627\u0631\u062f\u0647\u0627 \u0633\u0646\u062f \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u0646\u062f.  \u0628\u0631\u0627\u06cc \u0645\u062b\u0627\u0644 <a target=\"_blank\" href=\"https:\/\/code.google.com\/archive\/p\/word2vec\/\" rel=\"noopener\" class=\"broken_link\">\u0645\u062f\u0644 Word2Vec \u06af\u0648\u06af\u0644<\/a> \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 3 \u0645\u06cc\u0644\u06cc\u0648\u0646 \u06a9\u0644\u0645\u0647 \u0648 \u0639\u0628\u0627\u0631\u062a \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0628\u0631\u0627\u06cc \u0633\u0627\u062f\u06af\u06cc\u060c \u06cc\u06a9 \u0645\u062f\u0644 Word2Vec \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0645\u0642\u0627\u0644\u0647 \u0645\u0646\u0641\u0631\u062f \u0648\u06cc\u06a9\u06cc\u200c\u067e\u062f\u06cc\u0627 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645.  \u0645\u062f\u0644 \u0645\u0627 \u0628\u0647 \u062e\u0648\u0628\u06cc \u0645\u062f\u0644 \u06af\u0648\u06af\u0644 \u0646\u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.  \u0627\u06af\u0631\u0686\u0647\u060c \u062a\u0648\u0636\u06cc\u062d \u0627\u06cc\u0646\u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u062f\u0644 Word2Vec \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0631\u062f\u060c \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u06a9\u0627\u0641\u06cc \u062e\u0648\u0628 \u0627\u0633\u062a.<\/p>\n<p>\u0642\u0628\u0644 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0628\u062a\u0648\u0627\u0646\u06cc\u0645 \u0645\u0642\u0627\u0644\u0627\u062a \u0648\u06cc\u06a9\u06cc \u067e\u062f\u06cc\u0627 \u0631\u0627 \u062e\u0644\u0627\u0635\u0647 \u06a9\u0646\u06cc\u0645\u060c \u0628\u0627\u06cc\u062f \u0622\u0646\u0647\u0627 \u0631\u0627 \u0648\u0627\u06a9\u0634\u06cc \u06a9\u0646\u06cc\u0645.  \u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0627\u0632 \u0686\u0646\u062f \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.  \u0627\u0648\u0644\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0627\u06cc \u06a9\u0647 \u0628\u0627\u06cc\u062f \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0646\u06cc\u0645 \u0627\u06cc\u0646 \u0627\u0633\u062a <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/www.crummy.com\/software\/BeautifulSoup\/bs4\/doc\/\" class=\"broken_link\">\u0633\u0648\u067e \u0632\u06cc\u0628\u0627<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647\u060c \u06a9\u0647 \u06cc\u06a9 \u0627\u0628\u0632\u0627\u0631 \u0628\u0633\u06cc\u0627\u0631 \u0645\u0641\u06cc\u062f \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u0627\u0633\u06a9\u0631\u067e\u06cc\u0646\u06af \u0648\u0628 \u0627\u0633\u062a.  \u0628\u0631\u0627\u06cc \u062f\u0627\u0646\u0644\u0648\u062f \u0627\u0628\u0632\u0627\u0631 Beautiful Soup \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u062e\u0637 \u0641\u0631\u0645\u0627\u0646 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">$ pip install beautifulsoup4\n<\/code><\/pre>\n<p>\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0645\u0647\u0645 \u062f\u06cc\u06af\u0631\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 XML \u0648 HTML \u0628\u0647 \u0622\u0646 \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u0645\u060c \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0627\u0633\u062a <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/lxml.de\/\">lxml<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647  \u0628\u0631\u0627\u06cc \u062f\u0627\u0646\u0644\u0648\u062f lxml \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u062e\u0637 \u0641\u0631\u0645\u0627\u0646 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">$ pip install lxml\n<\/code><\/pre>\n<p>\u0645\u0642\u0627\u0644\u0647 \u0627\u06cc \u06a9\u0647 \u0645\u06cc\u062e\u0648\u0627\u0647\u06cc\u0645 \u0628\u0646\u0648\u06cc\u0633\u06cc\u0645 \u0645\u0642\u0627\u0644\u0647 \u0648\u06cc\u06a9\u06cc \u067e\u062f\u06cc\u0627 \u0627\u0633\u062a \u0631\u0648\u06cc <a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/en.wikipedia.org\/wiki\/Artificial_intelligence\">\u0647\u0648\u0634 \u0645\u0635\u0646\u0648\u0639\u06cc<\/a>.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0646\u0648\u06cc\u0633\u06cc\u0645 \u062a\u0627 \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u0627\u0632 \u0648\u06cc\u06a9\u06cc\u200c\u067e\u062f\u06cc\u0627 \u067e\u0627\u06a9 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> bs4 <span class=\"hljs-keyword\">as<\/span> bs\n<span class=\"hljs-keyword\">import<\/span> urllib.request\n<span class=\"hljs-keyword\">import<\/span> re\n<span class=\"hljs-keyword\">import<\/span> nltk\n\nscrapped_data = urllib.request.urlopen(<span class=\"hljs-string\">'https:\/\/en.wikipedia.org\/wiki\/Artificial_intelligence'<\/span>)\narticle = scrapped_data .read()\n\nparsed_article = bs.BeautifulSoup(article,<span class=\"hljs-string\">'lxml'<\/span>)\n\nparagraphs = parsed_article.find_all(<span class=\"hljs-string\">'p'<\/span>)\n\narticle_text = <span class=\"hljs-string\">\"\"<\/span>\n\n<span class=\"hljs-keyword\">for<\/span> p <span class=\"hljs-keyword\">in<\/span> paragraphs:\n    article_text += p.text\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0627\u0628\u062a\u062f\u0627 \u0645\u0642\u0627\u0644\u0647 \u0648\u06cc\u06a9\u06cc \u067e\u062f\u06cc\u0627 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>urlopen<\/code> \u0631\u0648\u0634 \u0627\u0632 <code>request<\/code> \u06a9\u0644\u0627\u0633 \u0627\u0632 <code>urllib<\/code> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647  \u0633\u067e\u0633 \u0645\u062d\u062a\u0648\u0627\u06cc \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u0645\u06cc \u062e\u0648\u0627\u0646\u06cc\u0645 \u0648 \u0622\u0646 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0634\u06cc \u0627\u0632 the \u062a\u062c\u0632\u06cc\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>BeautifulSoup<\/code> \u06a9\u0644\u0627\u0633  \u0648\u06cc\u06a9\u06cc \u067e\u062f\u06cc\u0627 \u0645\u062d\u062a\u0648\u0627\u06cc \u0645\u062a\u0646\u06cc \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u062f\u0631 \u062f\u0627\u062e\u0644 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u06a9\u0646\u062f <code>p<\/code> \u0628\u0631\u0686\u0633\u0628 \u0647\u0627  \u0645\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>find_all<\/code> \u0639\u0645\u0644\u06a9\u0631\u062f \u0627\u0632 <code>BeautifulSoup<\/code> \u0628\u0631\u0627\u06cc \u0648\u0627\u06a9\u0634\u06cc \u062a\u0645\u0627\u0645 \u0645\u062d\u062a\u0648\u06cc\u0627\u062a \u0627\u0632 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc \u067e\u0627\u0631\u0627\u06af\u0631\u0627\u0641 \u0645\u0642\u0627\u0644\u0647 \u0634\u06cc \u06a9\u0646\u06cc\u062f.<\/p>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u062a\u0645\u0627\u0645 \u067e\u0627\u0631\u0627\u06af\u0631\u0627\u0641 \u0647\u0627 \u0631\u0627 \u0628\u0647 \u0647\u0645 \u0645\u062a\u0635\u0644 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0645\u0642\u0627\u0644\u0647 \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u062f\u0647 \u0631\u0627 \u062f\u0631 \u0622\u0646 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>article_text<\/code> \u0645\u062a\u063a\u06cc\u0631 \u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0628\u0639\u062f\u06cc<\/p>\n<h3 id=\"preprocessing\"><span class=\"ez-toc-section\" id=\"%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4\"><\/span>\u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0631\u062d\u0644\u0647 \u0645\u0627 \u0627\u06a9\u0646\u0648\u0646 \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u0648\u0627\u0631\u062f \u06a9\u0631\u062f\u0647 \u0627\u06cc\u0645.  \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634 \u0645\u062d\u062a\u0648\u0627 \u0628\u0631\u0627\u06cc \u0645\u062f\u0644 Word2Vec \u0627\u0633\u062a.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0645\u062a\u0646 \u0631\u0627 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634 \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">\nprocessed_article = article_text.lower()\nprocessed_article = re.sub(<span class=\"hljs-string\">'(^a-zA-Z)'<\/span>, <span class=\"hljs-string\">' '<\/span>, processed_article )\nprocessed_article = re.sub(<span class=\"hljs-string\">r'\\s+'<\/span>, <span class=\"hljs-string\">' '<\/span>, processed_article)\n\n\nall_sentences = nltk.sent_tokenize(processed_article)\n\nall_words = (nltk.word_tokenize(sent) <span class=\"hljs-keyword\">for<\/span> sent <span class=\"hljs-keyword\">in<\/span> all_sentences)\n\n\n<span class=\"hljs-keyword\">from<\/span> nltk.corpus <span class=\"hljs-keyword\">import<\/span> stopwords\n<span class=\"hljs-keyword\">for<\/span> i <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-built_in\">range<\/span>(<span class=\"hljs-built_in\">len<\/span>(all_words)):\n    all_words(i) = (w <span class=\"hljs-keyword\">for<\/span> w <span class=\"hljs-keyword\">in<\/span> all_words(i) <span class=\"hljs-keyword\">if<\/span> w <span class=\"hljs-keyword\">not<\/span> <span class=\"hljs-keyword\">in<\/span> stopwords.words(<span class=\"hljs-string\">'english'<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u062a\u0645\u0627\u0645 \u0645\u062a\u0646 \u0631\u0627 \u0628\u0647 \u062d\u0631\u0648\u0641 \u06a9\u0648\u0686\u06a9 \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0633\u067e\u0633 \u062a\u0645\u0627\u0645 \u0627\u0631\u0642\u0627\u0645\u060c \u06a9\u0627\u0631\u0627\u06a9\u062a\u0631\u0647\u0627\u06cc \u062e\u0627\u0635 \u0648 \u0641\u0627\u0635\u0644\u0647 \u0647\u0627\u06cc \u0627\u0636\u0627\u0641\u06cc \u0631\u0627 \u0627\u0632 \u0645\u062a\u0646 \u062d\u0630\u0641 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u067e\u0633 \u0627\u0632 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634\u060c \u0641\u0642\u0637 \u06a9\u0644\u0645\u0627\u062a \u0628\u0627\u0642\u06cc \u0645\u06cc \u0645\u0627\u0646\u0646\u062f.<\/p>\n<p>\u0645\u062f\u0644 Word2Vec \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a  \u0627\u0628\u062a\u062f\u0627 \u0628\u0627\u06cc\u062f \u0645\u0642\u0627\u0644\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u062c\u0645\u0644\u0627\u062a \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u0645\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>nltk.sent_tokenize<\/code> \u0627\u0628\u0632\u0627\u0631\u06cc \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u0645\u0642\u0627\u0644\u0647 \u0645\u0627 \u0628\u0647 \u062c\u0645\u0644\u0627\u062a.  \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u062c\u0645\u0644\u0627\u062a \u0628\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>nltk.word_tokenize<\/code> \u0633\u0648\u062f\u0645\u0646\u062f\u06cc  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0622\u062e\u0631\u06cc\u0646 \u0645\u0631\u062d\u0644\u0647 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634\u060c \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u062a\u0648\u0642\u0641 \u0631\u0627 \u0627\u0632 \u0645\u062a\u0646 \u062d\u0630\u0641 \u0645\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u067e\u0633 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0627\u062c\u0631\u0627\u06cc \u062e\u0648\u062f \u0631\u0627 \u06a9\u0627\u0645\u0644 \u06a9\u0631\u062f\u060c <code>all_words<\/code> \u0634\u06cc \u0634\u0627\u0645\u0644 \u0644\u06cc\u0633\u062a\u06cc \u0627\u0632 \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0627\u0633\u062a.  \u0645\u0627 \u0627\u0632 \u0627\u06cc\u0646 \u0644\u06cc\u0633\u062a \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 Word2Vec \u062e\u0648\u062f \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.<\/p>\n<h3 id=\"creatingword2vecmodel\"><span class=\"ez-toc-section\" id=\"%d8%a7%db%8c%d8%ac%d8%a7%d8%af_%d9%85%d8%af%d9%84_word2vec\"><\/span>\u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 Word2Vec<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0628\u0627 Gensim\u060c \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 Word2Vec \u0628\u0633\u06cc\u0627\u0631 \u0633\u0627\u062f\u0647 \u0627\u0633\u062a.  \u0644\u06cc\u0633\u062a \u06a9\u0644\u0645\u0627\u062a \u0628\u0647 <code>Word2Vec<\/code> \u06a9\u0644\u0627\u0633 \u0627\u0632 <code>gensim.models<\/code> \u0628\u0633\u062a\u0647 \u0628\u0646\u062f\u06cc  \u0628\u0627\u06cc\u062f \u0645\u0642\u062f\u0627\u0631 \u0631\u0627 \u0628\u0631\u0627\u06cc the \u0645\u0634\u062e\u0635 \u06a9\u0646\u06cc\u0645 <code>min_count<\/code> \u067e\u0627\u0631\u0627\u0645\u062a\u0631.  \u0645\u0642\u062f\u0627\u0631 2 \u0628\u0631\u0627\u06cc <code>min_count<\/code> \u0645\u0634\u062e\u0635 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u0641\u0642\u0637 \u0622\u0646 \u062f\u0633\u062a\u0647 \u0627\u0632 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062f\u0631 \u0645\u062f\u0644 Word2Vec \u06a9\u0647 \u062d\u062f\u0627\u0642\u0644 \u062f\u0648 \u0628\u0627\u0631 \u062f\u0631 \u0628\u062f\u0646\u0647 \u0638\u0627\u0647\u0631 \u0645\u06cc \u0634\u0648\u0646\u062f \u0634\u0627\u0645\u0644 \u0634\u0648\u062f.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0645\u062f\u0644 Word2Vec \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0645\u0642\u0627\u0644\u0647 \u0648\u06cc\u06a9\u06cc\u200c\u067e\u062f\u06cc\u0627\u06cc\u06cc \u06a9\u0647 \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u06cc\u0645 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc\u200c\u06a9\u0646\u062f.<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> gensim.models <span class=\"hljs-keyword\">import<\/span> Word2Vec\n\nword2vec = Word2Vec(all_words, min_count=<span class=\"hljs-number\">2<\/span>)\n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u0645\u0634\u0627\u0647\u062f\u0647 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u06a9\u0647 \u062d\u062f\u0627\u0642\u0644 \u062f\u0648 \u0628\u0627\u0631 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f\u060c \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">vocabulary = word2vec.wv.vocab\n<span class=\"hljs-built_in\">print<\/span>(vocabulary)\n<\/code><\/pre>\n<p>\u0647\u0646\u06af\u0627\u0645\u06cc \u06a9\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u0627\u062c\u0631\u0627 \u0645\u06cc \u0634\u0648\u062f\u060c \u0644\u06cc\u0633\u062a\u06cc \u0627\u0632 \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0631\u0627 \u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u062d\u062f\u0627\u0642\u0644 \u062f\u0648 \u0628\u0627\u0631 \u0627\u062a\u0641\u0627\u0642 \u0645\u06cc \u0627\u0641\u062a\u062f.<\/p>\n<h3 id=\"modelanalysis\"><span class=\"ez-toc-section\" id=\"%d8%aa%d8%ad%d9%84%db%8c%d9%84_%d9%85%d8%af%d9%84\"><\/span>\u062a\u062d\u0644\u06cc\u0644 \u0645\u062f\u0644<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0645\u0627 \u0645\u062f\u0644 Word2Vec \u062e\u0648\u062f \u0631\u0627 \u062f\u0631 \u0628\u062e\u0634 \u0622\u062e\u0631 \u0628\u0627 \u0645\u0648\u0641\u0642\u06cc\u062a \u0627\u06cc\u062c\u0627\u062f \u06a9\u0631\u062f\u06cc\u0645.  \u0627\u06a9\u0646\u0648\u0646 \u0632\u0645\u0627\u0646 \u0622\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0622\u0646\u0686\u0647 \u0631\u0627 \u06a9\u0647 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0631\u062f\u0647 \u0627\u06cc\u0645 \u06a9\u0634\u0641 \u06a9\u0646\u06cc\u0645.<\/p>\n<h4 id=\"findingvectorsforaword\">\u067e\u06cc\u062f\u0627 \u06a9\u0631\u062f\u0646 \u0648\u06a9\u062a\u0648\u0631 \u0628\u0631\u0627\u06cc \u06cc\u06a9 \u06a9\u0644\u0645\u0647<\/h4>\n<p>\u0645\u06cc \u062f\u0627\u0646\u06cc\u0645 \u06a9\u0647 \u0645\u062f\u0644 Word2Vec \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u062a\u0646\u0627\u0638\u0631 \u0622\u0646\u0647\u0627 \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0646\u0645\u0627\u06cc\u0634 \u0628\u0631\u062f\u0627\u0631\u06cc \u0647\u0631 \u06a9\u0644\u0645\u0647 \u062e\u0627\u0635 \u0631\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0646\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\">v1 = word2vec.wv(<span class=\"hljs-string\">'artificial'<\/span>)\n<\/code><\/pre>\n<p>\u0628\u0631\u062f\u0627\u0631 <code>v1<\/code> \u062d\u0627\u0648\u06cc \u0646\u0645\u0627\u06cc\u0634 \u0628\u0631\u062f\u0627\u0631\u06cc \u0628\u0631\u0627\u06cc \u06a9\u0644\u0645\u0647 &#8220;\u0645\u0635\u0646\u0648\u0639\u06cc&#8221;.  \u0628\u0647 \u0637\u0648\u0631 \u067e\u06cc\u0634 \u0641\u0631\u0636\u060c \u0628\u0631\u062f\u0627\u0631 \u0635\u062f \u0628\u0639\u062f\u06cc \u062a\u0648\u0633\u0637 Gensim Word2Vec \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u062f.  \u0627\u06cc\u0646 \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 \u0628\u0633\u06cc\u0627\u0631 \u0628\u0633\u06cc\u0627\u0631 \u06a9\u0648\u0686\u06a9\u062a\u0631 \u062f\u0631 \u0645\u0642\u0627\u06cc\u0633\u0647 \u0628\u0627 \u0622\u0646\u0686\u0647 \u06a9\u0647 \u0628\u0627 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u062a\u0648\u0644\u06cc\u062f \u0645\u06cc \u0634\u062f \u0627\u0633\u062a.  \u0627\u06af\u0631 \u0627\u0632 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0628\u0631\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u0645\u0642\u0627\u0644\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645\u060c \u0637\u0648\u0644 \u0628\u0631\u062f\u0627\u0631 \u0628\u0631\u0627\u06cc \u0647\u0631 \u06cc\u06a9 1206 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f \u0632\u06cc\u0631\u0627 1206 \u06a9\u0644\u0645\u0647 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0628\u0627 \u062d\u062f\u0627\u0642\u0644 \u0641\u0631\u0627\u0648\u0627\u0646\u06cc 2 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f. \u0627\u06af\u0631 \u062d\u062f\u0627\u0642\u0644 \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u0648\u0642\u0648\u0639 \u0631\u0648\u06cc 1 \u062a\u0646\u0638\u06cc\u0645 \u0634\u0648\u062f\u060c \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u06a9\u062a\u0648\u0631 \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0628\u06cc\u0634\u062a\u0631 \u0627\u0641\u0632\u0627\u06cc\u0634 \u062e\u0648\u0627\u0647\u062f \u06cc\u0627\u0641\u062a.  \u0627\u0632 \u0633\u0648\u06cc \u062f\u06cc\u06af\u0631\u060c \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u062a\u0648\u0644\u06cc\u062f \u0634\u062f\u0647 \u0627\u0632 \u0637\u0631\u06cc\u0642 Word2Vec \u062a\u062d\u062a \u062a\u0623\u062b\u06cc\u0631 \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u0642\u0631\u0627\u0631 \u0646\u0645\u06cc \u06af\u06cc\u0631\u0646\u062f.<\/p>\n<h4 id=\"findingsimilarwords\">\u067e\u06cc\u062f\u0627 \u06a9\u0631\u062f\u0646 \u06a9\u0644\u0645\u0627\u062a \u0645\u0634\u0627\u0628\u0647<\/h4>\n<p>\u0642\u0628\u0644\u0627\u064b \u06af\u0641\u062a\u06cc\u0645 \u06a9\u0647 \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0645\u062a\u0646\u06cc \u06a9\u0644\u0645\u0627\u062a \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0631\u0648\u06cc\u06a9\u0631\u062f Word2Vec \u0627\u0632 \u0628\u06cc\u0646 \u0646\u0645\u06cc \u0631\u0648\u062f.  \u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0628\u0627 \u06cc\u0627\u0641\u062a\u0646 \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u0645\u0634\u0627\u0628\u0647 \u06a9\u0644\u0645\u0647 &#8220;\u0647\u0648\u0634&#8221; \u0627\u06cc\u0646 \u0645\u0648\u0636\u0648\u0639 \u0631\u0627 \u062a\u0623\u06cc\u06cc\u062f \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0628\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u062f\u0642\u062a \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">sim_words = word2vec.wv.most_similar(<span class=\"hljs-string\">'intelligence'<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06af\u0631 \u0634\u0645\u0627 print \u0631\u0627 <code>sim_words<\/code> \u0645\u062a\u063a\u06cc\u0631 \u0628\u0647 console\u060c \u0634\u0628\u06cc\u0647 \u062a\u0631\u06cc\u0646 \u06a9\u0644\u0645\u0627\u062a \u0628\u0647 &#8220;\u0647\u0648\u0634&#8221; \u0631\u0627 \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">('ai', 0.7124934196472168)\n('human', 0.6869025826454163)\n('artificial', 0.6208730936050415)\n('would', 0.583903431892395)\n('many', 0.5610555410385132)\n('also', 0.5557990670204163)\n('learning', 0.554862380027771)\n('search', 0.5522681474685669)\n('language', 0.5408136248588562)\n('include', 0.5248900055885315)\n<\/code><\/pre>\n<p>\u0627\u0632 \u062e\u0631\u0648\u062c\u06cc \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u06a9\u0644\u0645\u0627\u062a \u0645\u0634\u0627\u0628\u0647 &#8220;\u0647\u0648\u0634&#8221; \u0631\u0627 \u0628\u0647 \u0647\u0645\u0631\u0627\u0647 \u0634\u0627\u062e\u0635 \u0634\u0628\u0627\u0647\u062a \u0622\u0646\u0647\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0646\u06cc\u062f.  \u06a9\u0644\u0645\u0647 &#8220;ai&#8221; \u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 \u0645\u062f\u0644 \u0645\u0634\u0627\u0628\u0647 \u062a\u0631\u06cc\u0646 \u06a9\u0644\u0645\u0647 \u0628\u0647 &#8220;\u0647\u0648\u0634&#8221; \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0648\u0627\u0642\u0639 \u0645\u0639\u0646\u06cc \u062f\u0627\u0631\u062f.  \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062a\u0631\u062a\u06cc\u0628\u060c \u06a9\u0644\u0645\u0627\u062a\u06cc \u0645\u0627\u0646\u0646\u062f \u00ab\u0627\u0646\u0633\u0627\u0646\u00bb \u0648 \u00ab\u0645\u0635\u0646\u0648\u0639\u06cc\u00bb \u0627\u063a\u0644\u0628 \u0628\u0627 \u06a9\u0644\u0645\u0647 \u00ab\u0647\u0648\u0634\u00bb \u0647\u0645\u0632\u06cc\u0633\u062a\u06cc \u062f\u0627\u0631\u0646\u062f.  \u0645\u062f\u0644 \u0645\u0627 \u062a\u0646\u0647\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0645\u0642\u0627\u0644\u0647 \u0648\u06cc\u06a9\u06cc\u200c\u067e\u062f\u06cc\u0627\u060c \u0627\u06cc\u0646 \u0631\u0648\u0627\u0628\u0637 \u0631\u0627 \u0628\u0627 \u0645\u0648\u0641\u0642\u06cc\u062a \u062b\u0628\u062a \u06a9\u0631\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<h2 id=\"conclusion\"><span class=\"ez-toc-section\" id=\"%d9%86%d8%aa%db%8c%d8%ac%d9%87\"><\/span>\u0646\u062a\u06cc\u062c\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647\u060c \u0645\u0627 \u06cc\u06a9 \u0645\u062f\u0644 \u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0647 Word2Vec \u0631\u0627 \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim Python \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0631\u062f\u06cc\u0645.  \u0645\u0627 \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0631\u0627 \u0628\u0627 \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u06cc\u06a9 \u0645\u0642\u0627\u0644\u0647 \u0648\u06cc\u06a9\u06cc\u200c\u067e\u062f\u06cc\u0627 \u0627\u0646\u062c\u0627\u0645 \u062f\u0627\u062f\u06cc\u0645 \u0648 \u0645\u062f\u0644 Word2Vec \u062e\u0648\u062f \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0645\u062c\u0645\u0648\u0639\u0647 \u0633\u0627\u062e\u062a\u06cc\u0645.  \u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u062a\u062f\u0627\u0648\u0644 \u062a\u0631\u06cc\u0646 \u0631\u0648\u0634 \u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0631\u0627 \u0628\u0647 \u0647\u0645\u0631\u0627\u0647 \u0645\u0632\u0627\u06cc\u0627 \u0648 \u0645\u0639\u0627\u06cc\u0628 \u0622\u0646\u0647\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u0642\u0627\u06cc\u0633\u0647 \u0628\u0627 Word2Vec \u0645\u0631\u0648\u0631 \u06a9\u0631\u062f\u06cc\u0645.<\/p>\n<p>\u0645\u0646 \u0628\u0647 \u0634\u0645\u0627 \u067e\u06cc\u0634\u0646\u0647\u0627\u062f \u0645\u06cc\u200c\u06a9\u0646\u0645 \u0628\u0627 \u06a9\u0645\u06a9 \u0647\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u062a\u0646\u06cc \u06cc\u06a9 \u0645\u062f\u0644 Word2Vec \u0628\u0631\u0627\u06cc \u062e\u0648\u062f\u062a\u0627\u0646 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f \u0648 \u0628\u0628\u06cc\u0646\u06cc\u062f \u0622\u06cc\u0627 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u062f \u0646\u062a\u0627\u06cc\u062c \u0628\u0647\u062a\u0631\u06cc \u062f\u0631 \u0645\u0642\u0627\u06cc\u0633\u0647 \u0628\u0627 \u0631\u0648\u06cc\u06a9\u0631\u062f \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0628\u06af\u06cc\u0631\u06cc\u062f \u06cc\u0627 \u062e\u06cc\u0631.<\/p>\n<\/div>\n<p><script>\n                        !function(f,b,e,v,n,t,s)\n                        {if(f.fbq)return;n=f.fbq=function(){n.callMethod?\n                        n.callMethod.apply(n,arguments):n.queue.push(arguments)};\n                        if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';\n                        n.queue=();t=b.createElement(e);t.async=!0;\n                        t.src=v;s=b.getElementsByTagName(e)(0);\n                        s.parentNode.insertBefore(t,s)}(window, document,'script',\n                        'https:\/\/connect.facebook.net\/en_US\/fbevents.js');\n                        fbq('init', '525232124909042');\n                        fbq('track', 'PageView');\n                    <\/script>    (\u0628\u0631\u0686\u0633\u0628\u200c\u0647\u0627 \u0628\u0647 \u062a\u0631\u062c\u0645\u0647)# python<br \/>\n<br \/><br \/>\n<br \/>\u0645\u0646\u062a\u0634\u0631 \u0634\u062f\u0647 \u062f\u0631 1403-01-27 07:04:04<br \/>\n<\/p>\n\n\n<div class=\"kk-star-ratings kksr-auto kksr-align-center kksr-valign-bottom\"\n    data-payload='{&quot;align&quot;:&quot;center&quot;,&quot;id&quot;:&quot;16576&quot;,&quot;slug&quot;:&quot;default&quot;,&quot;valign&quot;:&quot;bottom&quot;,&quot;ignore&quot;:&quot;&quot;,&quot;reference&quot;:&quot;auto&quot;,&quot;class&quot;:&quot;&quot;,&quot;count&quot;:&quot;0&quot;,&quot;legendonly&quot;:&quot;&quot;,&quot;readonly&quot;:&quot;&quot;,&quot;score&quot;:&quot;0&quot;,&quot;starsonly&quot;:&quot;&quot;,&quot;best&quot;:&quot;5&quot;,&quot;gap&quot;:&quot;5&quot;,&quot;greet&quot;:&quot;\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628&quot;,&quot;legend&quot;:&quot;0\\\/5 (0 \u0631\u0627\u06cc)&quot;,&quot;size&quot;:&quot;30&quot;,&quot;title&quot;:&quot;\u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc Word2Vec \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Gensim \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646&quot;,&quot;width&quot;:&quot;0&quot;,&quot;_legend&quot;:&quot;{score}\\\/{best} ({count} \u0631\u0627\u06cc)&quot;,&quot;font_factor&quot;:&quot;1.25&quot;}'>\n            \n<div class=\"kksr-stars\">\n    \n<div class=\"kksr-stars-inactive\">\n            <div class=\"kksr-star\" data-star=\"1\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"2\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"3\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"4\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"5\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n    \n<div class=\"kksr-stars-active\" style=\"width: 0px;\">\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n<\/div>\n                \n\n<div class=\"kksr-legend\" style=\"font-size: 24px;\">\n            <span class=\"kksr-muted\">\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628<\/span>\n    <\/div>\n    <\/div>\n","protected":false},"excerpt":{"rendered":"<p><span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 10<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span>\u0645\u0639\u0631\u0641\u06cc \u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u062f\u0627\u0631\u0627\u06cc \u062a\u0648\u0627\u0646\u0627\u06cc\u06cc \u0637\u0628\u06cc\u0639\u06cc \u0628\u0631\u0627\u06cc \u062f\u0631\u06a9 \u0622\u0646\u0686\u0647 \u062f\u06cc\u06af\u0631\u0627\u0646 \u0645\u06cc \u06af\u0648\u06cc\u0646\u062f \u0648 \u0622\u0646\u0686\u0647 \u062f\u0631 \u067e\u0627\u0633\u062e \u0628\u0647 \u0622\u0646 \u0645\u06cc \u06af\u0648\u06cc\u0646\u062f\u060c \u062f\u0627\u0631\u0646\u062f. \u0627\u06cc\u0646 \u062a\u0648\u0627\u0646\u0627\u06cc\u06cc \u0628\u0627 \u062a\u0639\u0627\u0645\u0644 \u0645\u062f\u0627\u0648\u0645 \u0628\u0627 \u0627\u0641\u0631\u0627\u062f \u062f\u06cc\u06af\u0631 \u0648 \u062c\u0627\u0645\u0639\u0647 \u062f\u0631 \u0637\u0648\u0644 \u0633\u0627\u0644\u06cc\u0627\u0646 \u0645\u062a\u0645\u0627\u062f\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u062f. \u0632\u0628\u0627\u0646 \u0646\u0642\u0634 \u0628\u0633\u06cc\u0627\u0631 \u0645\u0647\u0645\u06cc \u062f\u0631 \u0631\u0648\u0634 \u062a\u0639\u0627\u0645\u0644 \u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u062f\u0627\u0631\u062f. \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u0627\u0646\u0633\u0627\u0646 \u0647\u0627 \u0628\u0631\u0627\u06cc \u062a\u0639\u0627\u0645\u0644 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":9759,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1743,620,1686],"tags":[],"class_list":["post-16576","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-python","category-programming","category-ai"],"acf":[],"_links":{"self":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16576","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/comments?post=16576"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16576\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media\/9759"}],"wp:attachment":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media?parent=16576"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=16576"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=16576"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}