{"id":16152,"date":"2024-01-21T10:51:24","date_gmt":"2024-01-21T07:21:24","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/"},"modified":"2024-01-21T10:51:24","modified_gmt":"2024-01-21T07:21:24","slug":"python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/","title":{"rendered":"Python for NLP: Word Embeddings for Deep Learning \u062f\u0631 Keras"},"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\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/#%d9%85%d8%b4%da%a9%d9%84%d8%a7%d8%aa_%d8%a8%d8%a7_%d8%b1%d9%88%db%8c%da%a9%d8%b1%d8%af%d9%87%d8%a7%db%8c_%d8%a8%d8%b1%d8%af%d8%a7%d8%b1_%d9%88%db%8c%da%98%da%af%db%8c_%d8%b1%d9%85%d8%b2%da%af%d8%b0%d8%a7%d8%b1%db%8c_%d8%b4%d8%af%d9%87_one-hot\" >\u0645\u0634\u06a9\u0644\u0627\u062a \u0628\u0627 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u0628\u0631\u062f\u0627\u0631 \u0648\u06cc\u0698\u06af\u06cc \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 One-Hot<\/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\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/#%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%d9%87%d8%a7%db%8c_%da%a9%d9%84%d9%85%d9%87\" >\u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\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\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/#%d9%be%db%8c%d8%a7%d8%af%d9%87_%d8%b3%d8%a7%d8%b2%db%8c_%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87_%d8%a8%d8%a7_%d9%85%d8%af%d9%84_%d9%87%d8%a7%db%8c_%d9%85%d8%aa%d9%88%d8%a7%d9%84%db%8c_keras\" >\u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 \u0645\u062f\u0644 \u0647\u0627\u06cc \u0645\u062a\u0648\u0627\u0644\u06cc Keras<\/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\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/#%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87_%d8%a8%d8%a7_keras_functional_api\" >\u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 Keras Functional API<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/python-for-nlp-word-embeddings-for-deep-learning-%d8%af%d8%b1-keras\/#%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\"> 14<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span><p> <br \/>\n<\/p>\n<div><noscript><\/noscript><\/p>\n<p>\u0627\u06cc\u0646 \u0634\u0627\u0646\u0632\u062f\u0647\u0645\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0632 \u0633\u0631\u06cc \u0645\u0642\u0627\u0644\u0627\u062a \u0645\u0646 \u0627\u0633\u062a \u0631\u0648\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc NLP.  \u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0642\u0628\u0644\u06cc \u062e\u0648\u062f \u062a\u0648\u0636\u06cc\u062d \u062f\u0627\u062f\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u062a\u06a9\u0646\u06cc\u06a9 N-Grams \u0628\u0631\u0627\u06cc \u062a\u0648\u0633\u0639\u0647 \u06cc\u06a9 \u067e\u0631\u06a9\u0646\u0646\u062f\u0647 \u0645\u062a\u0646 \u062e\u0648\u062f\u06a9\u0627\u0631 \u0633\u0627\u062f\u0647 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.  \u0645\u062f\u0644 N-Gram \u0627\u0633\u0627\u0633\u0627\u064b \u0631\u0627\u0647\u06cc \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0639\u062f\u062f\u06cc \u0627\u0633\u062a \u062a\u0627 \u0628\u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u062a\u0648\u0633\u0637 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627\u06cc \u0622\u0645\u0627\u0631\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.<\/p>\n<p>\u0642\u0628\u0644 \u0627\u0632 N-Grams\u060c \u0645\u062c\u0645\u0648\u0639\u0647 \u06a9\u0644\u0645\u0627\u062a \u0648 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc TF-IDF \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u062f\u0627\u062f\u0645\u060c \u06a9\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u0628\u0631\u0627\u06cc \u062a\u0648\u0644\u06cc\u062f \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0648\u06cc\u0698\u06af\u06cc \u0639\u062f\u062f\u06cc \u0627\u0632 \u062f\u0627\u062f\u0647\u200c\u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0646\u06cc\u0632 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0634\u0648\u062f.  \u062a\u0627\u06a9\u0646\u0648\u0646 \u0627\u0632 \u0631\u0648\u0634\u200c\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0645\u0627\u0634\u06cc\u0646\u06cc \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0648\u0638\u0627\u06cc\u0641 \u0645\u062e\u062a\u0644\u0641 NLP \u0645\u0627\u0646\u0646\u062f \u0637\u0628\u0642\u0647\u200c\u0628\u0646\u062f\u06cc \u0645\u062a\u0646\u060c \u0645\u062f\u0644\u200c\u0633\u0627\u0632\u06cc \u0645\u0648\u0636\u0648\u0639\u060c \u062a\u062d\u0644\u06cc\u0644 \u0627\u062d\u0633\u0627\u0633\u0627\u062a\u060c \u062e\u0644\u0627\u0635\u0647\u200c\u0633\u0627\u0632\u06cc \u0645\u062a\u0646 \u0648 \u063a\u06cc\u0631\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645. \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u062d\u062b \u062e\u0648\u062f \u0631\u0627 \u062f\u0631 \u0645\u0648\u0631\u062f \u062a\u06a9\u0646\u06cc\u06a9\u200c\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0628\u0631\u0627\u06cc NLP \u0622\u063a\u0627\u0632 \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0634\u0627\u0645\u0644 \u0627\u0646\u0648\u0627\u0639 \u0645\u062e\u062a\u0644\u0641\u06cc \u0627\u0632 \u0634\u0628\u06a9\u0647 \u0647\u0627\u06cc \u0639\u0635\u0628\u06cc \u0628\u0627 \u0627\u062a\u0635\u0627\u0644 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0647\u0633\u062a\u0646\u062f.  \u0627\u06cc\u0646 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627 \u0628\u0631\u0627\u06cc \u062d\u0644 \u0686\u0646\u062f\u06cc\u0646 \u06a9\u0627\u0631 \u067e\u06cc\u0686\u06cc\u062f\u0647 \u0645\u0627\u0646\u0646\u062f \u0645\u0627\u0634\u06cc\u0646\u200c\u0647\u0627\u06cc \u062e\u0648\u062f\u0631\u0627\u0646\u060c \u062a\u0648\u0644\u06cc\u062f \u062a\u0635\u0648\u06cc\u0631\u060c \u062a\u0642\u0633\u06cc\u0645\u200c\u0628\u0646\u062f\u06cc \u062a\u0635\u0648\u06cc\u0631 \u0648 \u063a\u06cc\u0631\u0647 \u06a9\u0627\u0631\u0622\u0645\u062f \u0647\u0633\u062a\u0646\u062f. \u0631\u0648\u0634\u200c\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0646\u06cc\u0632 \u0628\u0631\u0627\u06cc \u06a9\u0627\u0631\u0647\u0627\u06cc NLP \u06a9\u0627\u0645\u0644\u0627\u064b \u06a9\u0627\u0631\u0622\u0645\u062f \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647\u060c \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0631\u0627\u06cc \u06a9\u0627\u0631\u0647\u0627\u06cc NLP \u06a9\u0647 \u0634\u0627\u0645\u0644 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0647\u0633\u062a\u0646\u062f\u060c \u0645\u0637\u0627\u0644\u0639\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0648\u0638\u0627\u06cc\u0641 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0633\u0627\u062f\u0647 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0634\u0628\u06a9\u0647 \u0639\u0635\u0628\u06cc \u0639\u0645\u06cc\u0642 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f. <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/keras.io\/\">\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06a9\u0631\u0627\u0633<\/a>.<\/p>\n<h2 id=\"problemswithonehotencodedfeaturevectorapproaches\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%b4%da%a9%d9%84%d8%a7%d8%aa_%d8%a8%d8%a7_%d8%b1%d9%88%db%8c%da%a9%d8%b1%d8%af%d9%87%d8%a7%db%8c_%d8%a8%d8%b1%d8%af%d8%a7%d8%b1_%d9%88%db%8c%da%98%da%af%db%8c_%d8%b1%d9%85%d8%b2%da%af%d8%b0%d8%a7%d8%b1%db%8c_%d8%b4%d8%af%d9%87_one-hot\"><\/span>\u0645\u0634\u06a9\u0644\u0627\u062a \u0628\u0627 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u0628\u0631\u062f\u0627\u0631 \u0648\u06cc\u0698\u06af\u06cc \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 One-Hot<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u06cc\u06a9 \u0627\u0634\u06a9\u0627\u0644 \u0628\u0627\u0644\u0642\u0648\u0647 \u0628\u0627 \u0631\u0648\u06cc\u06a9\u0631\u062f\u0647\u0627\u06cc \u0628\u0631\u062f\u0627\u0631 \u0648\u06cc\u0698\u06af\u06cc \u06a9\u062f\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u06cc\u06a9\u0628\u0627\u0631\u0647 \u0645\u0627\u0646\u0646\u062f N-Grams\u060c \u06a9\u06cc\u0633\u0647 \u06a9\u0644\u0645\u0627\u062a \u0648 \u0631\u0648\u06cc\u06a9\u0631\u062f TF-IDF \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0628\u0631\u062f\u0627\u0631 \u0648\u06cc\u0698\u06af\u06cc \u0628\u0631\u0627\u06cc \u0647\u0631 \u0633\u0646\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0632\u0631\u06af \u0628\u0627\u0634\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0627\u06af\u0631 \u0646\u06cc\u0645 \u0645\u06cc\u0644\u06cc\u0648\u0646 \u06a9\u0644\u0645\u0647 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u062f\u0627\u0631\u06cc\u062f \u0648 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u062c\u0645\u0644\u0647 \u0627\u06cc \u0631\u0627 \u0646\u0634\u0627\u0646 \u062f\u0647\u06cc\u062f \u06a9\u0647 \u0634\u0627\u0645\u0644 10 \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a\u060c \u0628\u0631\u062f\u0627\u0631 \u0648\u06cc\u0698\u06af\u06cc \u0634\u0645\u0627 \u0646\u06cc\u0645 \u0645\u06cc\u0644\u06cc\u0648\u0646 \u0628\u0631\u062f\u0627\u0631 \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u062a\u06a9 \u0628\u0639\u062f\u06cc \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u062a\u0646\u0647\u0627 10 \u0646\u0645\u0627\u06cc\u0647 \u062f\u0627\u0631\u0627\u06cc 1 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f. \u0627\u062a\u0644\u0627\u0641 \u0641\u0636\u0627 \u0648 \u0627\u0641\u0632\u0627\u06cc\u0634 \u0646\u0645\u0627\u06cc\u06cc \u067e\u06cc\u0686\u06cc\u062f\u06af\u06cc \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0645\u0646\u062c\u0631 \u0628\u0647 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Curse_of_dimensionality\">\u0646\u0641\u0631\u06cc\u0646 \u0627\u0628\u0639\u0627\u062f<\/a>.<\/p>\n<h2 id=\"wordembeddings\"><span class=\"ez-toc-section\" id=\"%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%d9%87%d8%a7%db%8c_%da%a9%d9%84%d9%85%d9%87\"><\/span>\u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u062f\u0631 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647\u060c \u0647\u0631 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 \u0645\u062a\u0631\u0627\u06a9\u0645 n \u0628\u0639\u062f\u06cc \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u06a9\u0644\u0645\u0627\u062a\u06cc \u06a9\u0647 \u0645\u0634\u0627\u0628\u0647 \u0647\u0633\u062a\u0646\u062f \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u0634\u0627\u0628\u0647\u06cc \u062e\u0648\u0627\u0647\u0646\u062f \u062f\u0627\u0634\u062a.  \u062a\u06a9\u0646\u06cc\u06a9 \u0647\u0627\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0645\u0627\u0646\u0646\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/GloVe_(machine_learning)\">\u062f\u0633\u062a\u06a9\u0634<\/a> \u0648 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Word2vec\">Word2Vec<\/a> \u062b\u0627\u0628\u062a \u06a9\u0631\u062f\u0647 \u0627\u0646\u062f \u06a9\u0647 \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\u0631\u0627\u06a9\u0645 \u0645\u062a\u0646\u0627\u0638\u0631 \u0628\u0633\u06cc\u0627\u0631 \u06a9\u0627\u0631\u0622\u0645\u062f \u0647\u0633\u062a\u0646\u062f.  \u0627\u0646\u062f\u0627\u0632\u0647 \u0628\u0631\u062f\u0627\u0631\u06cc \u06a9\u0648\u0686\u06a9 \u0627\u0633\u062a \u0648 \u0647\u06cc\u0686 \u06cc\u06a9 \u0627\u0632 \u0634\u0627\u062e\u0635 \u0647\u0627\u06cc \u0628\u0631\u062f\u0627\u0631 \u062f\u0631 \u0648\u0627\u0642\u0639 \u062e\u0627\u0644\u06cc \u0646\u06cc\u0633\u062a\u0646\u062f.<\/p>\n<h3 id=\"implementingwordembeddingswithkerassequentialmodels\"><span class=\"ez-toc-section\" id=\"%d9%be%db%8c%d8%a7%d8%af%d9%87_%d8%b3%d8%a7%d8%b2%db%8c_%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87_%d8%a8%d8%a7_%d9%85%d8%af%d9%84_%d9%87%d8%a7%db%8c_%d9%85%d8%aa%d9%88%d8%a7%d9%84%db%8c_keras\"><\/span>\u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 \u0645\u062f\u0644 \u0647\u0627\u06cc \u0645\u062a\u0648\u0627\u0644\u06cc Keras<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Keras \u06cc\u06a9\u06cc \u0627\u0632 \u0645\u0639\u0631\u0648\u0641 \u062a\u0631\u06cc\u0646 \u0648 \u067e\u0631\u06a9\u0627\u0631\u0628\u0631\u062f\u062a\u0631\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0628\u0631\u0627\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0633\u0627\u062e\u062a\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u0628\u0627\u0644\u0627\u06cc <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.tensorflow.org\/\" class=\"broken_link\">TensorFlow<\/a>.<\/p>\n<p>Keras \u0627\u0632 \u062f\u0648 \u0646\u0648\u0639 API \u067e\u0634\u062a\u06cc\u0628\u0627\u0646\u06cc \u0645\u06cc \u06a9\u0646\u062f: Sequential \u0648 Functional.  \u062f\u0631 \u0627\u06cc\u0646 \u0628\u062e\u0634 \u0645\u06cc \u0628\u06cc\u0646\u06cc\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 embedding \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 Keras Sequential API \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u062f\u0631 \u0628\u062e\u0634 \u0628\u0639\u062f\u06cc \u0631\u0648\u0634 \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0647\u0645\u0627\u0646 \u0645\u062f\u0644 \u0627\u0632 \u0637\u0631\u06cc\u0642 API \u0639\u0645\u0644\u06a9\u0631\u062f\u06cc Keras \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u062e\u0648\u0627\u0647\u0645 \u062f\u0627\u062f.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a\u060c \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Keras \u062d\u0627\u0648\u06cc \u0644\u0627\u06cc\u0647 \u0627\u06cc \u0628\u0647 \u0646\u0627\u0645 \u0627\u0633\u062a <code>Embedding()<\/code>.  \u0644\u0627\u06cc\u0647 embedding \u0628\u0647 \u0634\u06a9\u0644 \u06cc\u06a9 \u06a9\u0644\u0627\u0633 \u062f\u0631 Keras \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0645\u06cc \u0634\u0648\u062f \u0648 \u0645\u0639\u0645\u0648\u0644\u0627\u064b \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0627\u0648\u0644\u06cc\u0646 \u0644\u0627\u06cc\u0647 \u062f\u0631 \u0645\u062f\u0644 \u0645\u062a\u0648\u0627\u0644\u06cc \u0628\u0631\u0627\u06cc \u0648\u0638\u0627\u06cc\u0641 NLP \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0644\u0627\u06cc\u0647 embedding \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0633\u0647 \u06a9\u0627\u0631 \u062f\u0631 Keras \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f:<\/p>\n<ul>\n<li>\u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u0628\u0631\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0648 \u0630\u062e\u06cc\u0631\u0647 \u0645\u062f\u0644 \u0628\u0647 \u062f\u0633\u062a \u0622\u0645\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f<\/li>\n<li>\u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0627\u0646\u062c\u0627\u0645 \u0648\u0638\u0627\u06cc\u0641 NLP \u0645\u0627\u0646\u0646\u062f \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0645\u062a\u0646\u060c \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u0627\u062d\u0633\u0627\u0633\u0627\u062a \u0648 \u063a\u06cc\u0631\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u0628\u0631\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0648\u0627\u0698\u0647 \u0647\u0627\u06cc embedding \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.<\/li>\n<li>\u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u0628\u0631\u0627\u06cc \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u06a9\u0644\u0645\u0627\u062a \u0627\u0632 \u0642\u0628\u0644 \u0622\u0645\u0648\u0632\u0634 \u062f\u06cc\u062f\u0647 \u0648 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0622\u0646\u0647\u0627 \u062f\u0631 \u0645\u062f\u0644 \u062c\u062f\u06cc\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f<\/li>\n<\/ul>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u06a9\u0627\u0631\u0628\u0631\u062f \u062f\u0648\u0645 \u0648 \u0633\u0648\u0645 \u0644\u0627\u06cc\u0647 Embedding \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f.  \u0645\u0648\u0631\u062f \u0627\u0648\u0644 \u0632\u06cc\u0631\u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0648\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062f\u0648\u0645 \u0627\u0633\u062a.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0644\u0627\u06cc\u0647 embedding \u0686\u06af\u0648\u0646\u0647 \u0628\u0647 \u0646\u0638\u0631 \u0645\u06cc \u0631\u0633\u062f:<\/p>\n<pre><code class=\"hljs\">embedding_layer = Embedding(<span class=\"hljs-number\">200<\/span>, <span class=\"hljs-number\">32<\/span>, input_length=<span class=\"hljs-number\">50<\/span>)\n<\/code><\/pre>\n<p>\u0627\u0648\u0644\u06cc\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0631 \u0644\u0627\u06cc\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc\u060c \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u06cc\u0627 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u06cc\u06a9 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u0633\u062a.  \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0648\u0645 \u062a\u0639\u062f\u0627\u062f \u0627\u0628\u0639\u0627\u062f \u0647\u0631 \u0628\u0631\u062f\u0627\u0631 \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u0647\u0631 \u0628\u0631\u062f\u0627\u0631 \u06a9\u0644\u0645\u0647 32 \u0628\u0639\u062f \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u062f\u060c 32 \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0648\u0645 \u0645\u0634\u062e\u0635 \u0645\u06cc \u06a9\u0646\u06cc\u062f.  \u0648 \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0633\u0648\u0645 \u0637\u0648\u0644 \u062c\u0645\u0644\u0647 \u0648\u0631\u0648\u062f\u06cc \u0627\u0633\u062a.<\/p>\n<p>\u062e\u0631\u0648\u062c\u06cc \u06a9\u0644\u0645\u0647 embedding \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 \u062f\u0648\u0628\u0639\u062f\u06cc \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u06a9\u0644\u0645\u0627\u062a \u062f\u0631 \u0631\u062f\u06cc\u0641 \u0647\u0627 \u0646\u0645\u0627\u06cc\u0634 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u0646\u062f\u060c \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u0627\u0628\u0639\u0627\u062f \u0645\u062a\u0646\u0627\u0638\u0631 \u0622\u0646\u0647\u0627 \u062f\u0631 \u0633\u062a\u0648\u0646 \u0647\u0627 \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u0644\u0627\u06cc\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u062e\u0648\u062f \u0631\u0627 \u0645\u0633\u062a\u0642\u06cc\u0645\u0627\u064b \u0628\u0627 \u0644\u0627\u06cc\u0647 \u0627\u06cc \u0645\u062a\u0631\u0627\u06a9\u0645 \u0645\u062a\u0635\u0644 \u06a9\u0646\u06cc\u062f\u060c \u0627\u0628\u062a\u062f\u0627 \u0628\u0627\u06cc\u062f \u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u062f\u0648 \u0628\u0639\u062f\u06cc \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u06cc\u06a9 \u0628\u0639\u062f\u06cc \u0635\u0627\u0641 \u06a9\u0646\u06cc\u062f.  \u0627\u06cc\u0646 \u0645\u0641\u0627\u0647\u06cc\u0645 \u0632\u0645\u0627\u0646\u06cc \u0642\u0627\u0628\u0644 \u062f\u0631\u06a9 \u062a\u0631 \u0645\u06cc \u0634\u0648\u0646\u062f \u06a9\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0631\u0627 \u062f\u0631 \u0639\u0645\u0644 \u0628\u0628\u06cc\u0646\u06cc\u0645.<\/p>\n<h4 id=\"customwordembeddings\">\u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0627\u062a \u0633\u0641\u0627\u0631\u0634\u06cc<\/h4>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0642\u0628\u0644\u0627\u064b \u06af\u0641\u062a\u0645\u060c Keras \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u0628\u0631\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0633\u0641\u0627\u0631\u0634\u06cc \u06cc\u0627 \u0628\u0631\u0627\u06cc \u0628\u0627\u0631\u06af\u06cc\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0627\u062a \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0634\u0648\u062f.  \u062f\u0631 \u0627\u06cc\u0646 \u0642\u0633\u0645\u062a \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u0644\u0627\u06cc\u0647 Keras Embedding \u0628\u0631\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0633\u0641\u0627\u0631\u0634\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.<\/p>\n<p>\u0645\u0627 \u0648\u0638\u0627\u06cc\u0641 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0645\u062a\u0646 \u0633\u0627\u062f\u0647 \u0627\u06cc \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u0627\u062f \u06a9\u0647 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u0646\u062f.  \u0628\u0631\u0627\u06cc \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0646\u06cc\u0627\u0632 \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\"><span class=\"hljs-keyword\">from<\/span> numpy <span class=\"hljs-keyword\">import<\/span> array\n<span class=\"hljs-keyword\">from<\/span> keras.preprocessing.text <span class=\"hljs-keyword\">import<\/span> one_hot\n<span class=\"hljs-keyword\">from<\/span> keras.preprocessing.sequence <span class=\"hljs-keyword\">import<\/span> pad_sequences\n<span class=\"hljs-keyword\">from<\/span> keras.models <span class=\"hljs-keyword\">import<\/span> Sequential\n<span class=\"hljs-keyword\">from<\/span> keras.layers <span class=\"hljs-keyword\">import<\/span> Dense\n<span class=\"hljs-keyword\">from<\/span> keras.layers <span class=\"hljs-keyword\">import<\/span> Flatten\n<span class=\"hljs-keyword\">from<\/span> keras.layers.embeddings <span class=\"hljs-keyword\">import<\/span> Embedding\n<\/code><\/pre>\n<p>\u0628\u0639\u062f\u060c \u0628\u0627\u06cc\u062f \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u062e\u0648\u062f \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u06a9\u0646\u06cc\u0645.  \u0645\u0627 \u0627\u0632 \u06cc\u06a9 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0633\u0641\u0627\u0631\u0634\u06cc \u0628\u0633\u06cc\u0627\u0631 \u0633\u0627\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f \u06a9\u0647 \u062d\u0627\u0648\u06cc \u0646\u0638\u0631\u0627\u062a \u0628\u0627\u0644\u0627\u06cc \u0641\u06cc\u0644\u0645 \u0647\u0627 \u0627\u0633\u062a.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0645\u0627 \u0631\u0627 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">corpus = (\n    \n\n    <span class=\"hljs-string\">'This is an excellent movie'<\/span>,\n    <span class=\"hljs-string\">'The move was fantastic I like it'<\/span>,\n    <span class=\"hljs-string\">'You should watch it is brilliant'<\/span>,\n    <span class=\"hljs-string\">'Exceptionally good'<\/span>,\n    <span class=\"hljs-string\">'Wonderfully directed and executed I like it'<\/span>,\n    <span class=\"hljs-string\">'It'<\/span>s a fantastic series<span class=\"hljs-string\">',\n    '<\/span>Never watched such a brilliant movie<span class=\"hljs-string\">',\n    '<\/span>It <span class=\"hljs-keyword\">is<\/span> a Wonderful movie<span class=\"hljs-string\">',\n\n    # Negative Reviews\n\n    \"horrible acting\",\n    '<\/span>waste of money<span class=\"hljs-string\">',\n    '<\/span>pathetic picture<span class=\"hljs-string\">',\n    '<\/span>It was very boring<span class=\"hljs-string\">',\n    '<\/span>I did <span class=\"hljs-keyword\">not<\/span> like the movie<span class=\"hljs-string\">',\n    '<\/span>The movie was horrible<span class=\"hljs-string\">',\n    '<\/span>I will <span class=\"hljs-keyword\">not<\/span> recommend<span class=\"hljs-string\">',\n    '<\/span>The acting <span class=\"hljs-keyword\">is<\/span> pathetic<span class=\"hljs-string\">'\n)\n<\/span><\/code><\/pre>\n<p>\u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627 \u062f\u0627\u0631\u0627\u06cc 8 \u0628\u0631\u0631\u0633\u06cc \u0645\u062b\u0628\u062a \u0648 8 \u0628\u0631\u0631\u0633\u06cc \u0645\u0646\u0641\u06cc \u0627\u0633\u062a.  \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u06cc\u06a9 \u0645\u062c\u0645\u0648\u0639\u0647 \u0628\u0631\u0686\u0633\u0628 \u0628\u0631\u0627\u06cc \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u062e\u0648\u062f \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\">sentiments = array((<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>))\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 8 \u0645\u0648\u0631\u062f \u0627\u0648\u0644 \u062f\u0631 \u0622\u0631\u0627\u06cc\u0647 \u0627\u062d\u0633\u0627\u0633\u0627\u062a \u062d\u0627\u0648\u06cc 1 \u0627\u0633\u062a \u06a9\u0647 \u0628\u0627 \u0627\u062d\u0633\u0627\u0633\u0627\u062a \u0645\u062b\u0628\u062a \u0645\u0637\u0627\u0628\u0642\u062a \u062f\u0627\u0631\u062f.  8 \u0645\u0648\u0631\u062f \u0622\u062e\u0631 \u0635\u0641\u0631 \u0647\u0633\u062a\u0646\u062f \u06a9\u0647 \u0628\u0627 \u0627\u062d\u0633\u0627\u0633\u0627\u062a \u0645\u0646\u0641\u06cc \u0645\u0637\u0627\u0628\u0642\u062a \u062f\u0627\u0631\u0646\u062f.<\/p>\n<p>\u0642\u0628\u0644\u0627\u064b \u06af\u0641\u062a\u06cc\u0645 \u06a9\u0647 \u0627\u0648\u0644\u06cc\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0628\u0647 <code>Embedding()<\/code> \u0644\u0627\u06cc\u0647\u060c \u0648\u0627\u0698\u06af\u0627\u0646 \u06cc\u0627 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u0633\u062a.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u0628\u062a\u062f\u0627 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644 \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> nltk.tokenize <span class=\"hljs-keyword\">import<\/span> word_tokenize\n\nall_words = ()\n<span class=\"hljs-keyword\">for<\/span> sent <span class=\"hljs-keyword\">in<\/span> corpus:\n    tokenize_word = word_tokenize(sent)\n    <span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> tokenize_word:\n        all_words.append(word)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0645\u0627 \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u0647\u0631 \u062c\u0645\u0644\u0647 \u0631\u0627 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u062a\u06a9\u0631\u0627\u0631 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0633\u067e\u0633 \u062c\u0645\u0644\u0647 \u0631\u0627 \u0628\u0647 \u06a9\u0644\u0645\u0627\u062a \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u062f\u0631 \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u060c \u0644\u06cc\u0633\u062a \u0647\u0645\u0647 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062a\u06a9\u0631\u0627\u0631 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0647 \u0622\u0646 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>all_words<\/code> \u0641\u0647\u0631\u0633\u062a  \u067e\u0633 \u0627\u0632 \u0627\u062c\u0631\u0627\u06cc \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0628\u0627\u06cc\u062f \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0622\u0646 \u0631\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0646\u06cc\u062f <code>all_words<\/code> \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0645\u0627 \u06a9\u0644\u0645\u0627\u062a \u062a\u06a9\u0631\u0627\u0631\u06cc \u0631\u0627 \u0646\u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645.<\/p>\n<p>\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u062a\u0645\u0627\u0645 \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0631\u0627 \u0628\u0627 \u0627\u0631\u0633\u0627\u0644 \u0644\u06cc\u0633\u062a \u0628\u0647 \u0644\u06cc\u0633\u062a \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u06a9\u0646\u06cc\u0645 <code>set<\/code> \u0639\u0645\u0644\u06a9\u0631\u062f\u060c \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.<\/p>\n<pre><code class=\"hljs\">unique_words = <span class=\"hljs-built_in\">set<\/span>(all_words)\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-built_in\">len<\/span>(unique_words))\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc &#8220;45&#8221; \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f \u06a9\u0647 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627 \u0627\u0633\u062a.  \u06cc\u06a9 \u0628\u0627\u0641\u0631 5 \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u062e\u0648\u062f \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0645\u0642\u062f\u0627\u0631 \u0622\u0646 \u0631\u0627 \u062a\u0639\u06cc\u06cc\u0646 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>vocab_length<\/code> \u062a\u0627 50<\/p>\n<p>\u0644\u0627\u06cc\u0647 Embedding \u0627\u0646\u062a\u0638\u0627\u0631 \u062f\u0627\u0631\u062f \u06a9\u0647 \u06a9\u0644\u0645\u0627\u062a \u0628\u0647 \u0634\u06a9\u0644 \u0639\u062f\u062f\u06cc \u0628\u0627\u0634\u0646\u062f.  \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646\u060c \u0628\u0627\u06cc\u062f \u062c\u0645\u0644\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0639\u062f\u062f \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u06cc\u06a9\u06cc \u0627\u0632 \u0631\u0627\u0647 \u0647\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u0645\u062a\u0646 \u0628\u0647 \u0627\u0639\u062f\u0627\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>one_hot<\/code> \u062a\u0627\u0628\u0639 \u0627\u0632 <code>keras.preprocessing.text<\/code> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647  \u062a\u0627\u0628\u0639 \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u0648 \u0637\u0648\u0644 \u06a9\u0644 \u0648\u0627\u0698\u06af\u0627\u0646 \u0631\u0627 \u0645\u06cc \u06af\u06cc\u0631\u062f \u0648 \u062c\u0645\u0644\u0647 \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0639\u062f\u062f\u06cc \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u0627\u0646\u062f.<\/p>\n<pre><code class=\"hljs\">embedded_sentences = (one_hot(sent, vocab_length) <span class=\"hljs-keyword\">for<\/span> sent <span class=\"hljs-keyword\">in<\/span> corpus)\n<span class=\"hljs-built_in\">print<\/span>(embedded_sentences )\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u062a\u0645\u0627\u0645 \u062c\u0645\u0644\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0634\u06a9\u0644 \u0639\u062f\u062f\u06cc \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0631\u062f\u0647 \u0648 \u0646\u0645\u0627\u06cc\u0634 \u0645\u06cc \u062f\u0647\u06cc\u0645 \u0631\u0648\u06cc \u0631\u0627 console.  \u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">((31, 12, 31, 14, 9), (20, 3, 20, 16, 18, 45, 14), (16, 26, 29, 14, 12, 1), (16, 23), (32, 41, 13, 20, 18, 45, 14), (15, 28, 16, 43), (7, 9, 31, 28, 31, 9), (14, 12, 28, 46, 9), (4, 22), (5, 4, 9), (23, 46), (14, 20, 32, 14), (18, 1, 26, 45, 20, 9), (20, 9, 20, 4), (18, 8, 26, 34), (20, 22, 12, 23))\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0627\u0648\u0644\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0645\u0627 \u0634\u0627\u0645\u0644 \u067e\u0646\u062c \u06a9\u0644\u0645\u0647 \u0628\u0648\u062f\u060c \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u062f\u0631 \u0627\u0648\u0644\u06cc\u0646 \u0645\u0648\u0631\u062f \u0644\u06cc\u0633\u062a \u067e\u0646\u062c \u0639\u062f\u062f \u0635\u062d\u06cc\u062d \u062f\u0627\u0631\u06cc\u0645.  \u0647\u0645\u0686\u0646\u06cc\u0646 \u062a\u0648\u062c\u0647 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u06a9\u0647 \u0622\u062e\u0631\u06cc\u0646 \u06a9\u0644\u0645\u0647 \u062c\u0645\u0644\u0647 \u0627\u0648\u0644 \u062f\u0631 \u0627\u0648\u0644\u06cc\u0646 \u0645\u0648\u0631\u062f \u0644\u06cc\u0633\u062a &#8220;\u0641\u06cc\u0644\u0645&#8221; \u0628\u0648\u062f \u0648 \u062f\u0631 \u067e\u0646\u062c\u0645\u06cc\u0646 \u0645\u06a9\u0627\u0646 \u0622\u0631\u0627\u06cc\u0647 \u062f\u0648 \u0628\u0639\u062f\u06cc \u062d\u0627\u0635\u0644 \u0631\u0642\u0645 9 \u0631\u0627 \u062f\u0627\u0631\u06cc\u0645\u060c \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0639\u0646\u06cc \u06a9\u0647 &#8220;\u0641\u06cc\u0644\u0645&#8221; \u0628\u0647 \u0635\u0648\u0631\u062a 9 \u0648 \u063a\u06cc\u0631\u0647 \u06a9\u062f\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0627\u0633\u062a. \u0631\u0648\u06cc.<\/p>\n<p>\u0644\u0627\u06cc\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u0627\u0646\u062a\u0638\u0627\u0631 \u062f\u0627\u0631\u062f \u062c\u0645\u0644\u0627\u062a \u0628\u0627 \u0627\u0646\u062f\u0627\u0632\u0647 \u06cc\u06a9\u0633\u0627\u0646 \u0628\u0627\u0634\u0646\u062f.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u062c\u0645\u0644\u0627\u062a \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0645\u0627 \u0627\u0646\u062f\u0627\u0632\u0647 \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641\u06cc \u062f\u0627\u0631\u0646\u062f.  \u06cc\u06a9\u06cc \u0627\u0632 \u0631\u0627\u0647 \u0647\u0627\u06cc \u06cc\u06a9\u0646\u0648\u0627\u062e\u062a \u06a9\u0631\u062f\u0646 \u0647\u0645\u0647 \u062c\u0645\u0644\u0627\u062a \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0637\u0648\u0644 \u062a\u0645\u0627\u0645 \u062c\u0645\u0644\u0627\u062a \u0631\u0627 \u0627\u0641\u0632\u0627\u06cc\u0634 \u062f\u0627\u062f\u0647 \u0648 \u0622\u0646 \u0631\u0627 \u0628\u0627 \u0637\u0648\u0644 \u0628\u0632\u0631\u06af\u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0628\u0631\u0627\u0628\u0631 \u06a9\u0646\u06cc\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u0628\u062a\u062f\u0627 \u0628\u0632\u0631\u06af\u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0631\u0627 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u0645 \u0648 \u0633\u067e\u0633 \u0637\u0648\u0644 \u062a\u0645\u0627\u0645 \u062c\u0645\u0644\u0627\u062a \u0631\u0627 \u0628\u0647 \u0637\u0648\u0644 \u0628\u0632\u0631\u06af\u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0627\u0641\u0632\u0627\u06cc\u0634 \u062f\u0647\u06cc\u0645.  \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u06cc\u0646 \u06a9\u0627\u0631\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\">word_count = <span class=\"hljs-keyword\">lambda<\/span> sentence: <span class=\"hljs-built_in\">len<\/span>(word_tokenize(sentence))\nlongest_sentence = <span class=\"hljs-built_in\">max<\/span>(corpus, key=word_count)\nlength_long_sentence = <span class=\"hljs-built_in\">len<\/span>(word_tokenize(longest_sentence))\n<\/code><\/pre>\n<p>\u062f\u0631 \u062c\u0645\u0644\u0647 \u0628\u0627\u0644\u0627 \u0627\u0632 \u0639\u0628\u0627\u0631\u062a \u0644\u0627\u0645\u0628\u062f\u0627 \u0628\u0631\u0627\u06cc \u06cc\u0627\u0641\u062a\u0646 \u0637\u0648\u0644 \u062a\u0645\u0627\u0645 \u062c\u0645\u0644\u0627\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u0633\u067e\u0633 \u0627\u0632 <code>max<\/code> \u062a\u0627\u0628\u0639\u06cc \u0628\u0631\u0627\u06cc \u0628\u0631\u06af\u0631\u062f\u0627\u0646\u062f\u0646 \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0628\u0647 \u06a9\u0644\u0645\u0627\u062a \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u0634\u0648\u062f \u0648 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0622\u0646 \u0634\u0645\u0627\u0631\u0634 \u0645\u06cc \u0634\u0648\u062f <code>len<\/code> \u062a\u0627\u0628\u0639.<\/p>\n<p>\u0628\u0639\u062f \u0628\u0631\u0627\u06cc \u0627\u06cc\u0646\u06a9\u0647 \u0647\u0645\u0647 \u062c\u0645\u0644\u0627\u062a \u0628\u0627 \u0627\u0646\u062f\u0627\u0632\u0647 \u06cc\u06a9\u0633\u0627\u0646 \u0628\u0627\u0634\u0646\u062f\u060c \u0628\u0647 \u0627\u0646\u062f\u06cc\u0633 \u0647\u0627\u06cc \u062e\u0627\u0644\u06cc \u06a9\u0647 \u062f\u0631 \u0646\u062a\u06cc\u062c\u0647 \u0627\u0641\u0632\u0627\u06cc\u0634 \u0637\u0648\u0644 \u062c\u0645\u0644\u0647 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u0646\u062f\u060c \u0635\u0641\u0631 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u0628\u0631\u0627\u06cc \u0627\u0636\u0627\u0641\u0647 \u06a9\u0631\u062f\u0646 \u0635\u0641\u0631\u0647\u0627 \u062f\u0631 \u0627\u0646\u062a\u0647\u0627\u06cc \u062c\u0645\u0644\u0627\u062a\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0627\u0632 \u0639\u0628\u0627\u0631\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645 <code>pad_sequences<\/code> \u0631\u0648\u0634.  \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0627\u0648\u0644 \u0644\u06cc\u0633\u062a\u06cc \u0627\u0632 \u062c\u0645\u0644\u0627\u062a \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0628\u0627 \u0627\u0646\u062f\u0627\u0632\u0647 \u0647\u0627\u06cc \u0646\u0627\u0628\u0631\u0627\u0628\u0631\u060c \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0648\u0645 \u0627\u0646\u062f\u0627\u0632\u0647 \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u06cc\u0627 \u0634\u0627\u062e\u0635 padding \u0627\u0633\u062a\u060c \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u0622\u062e\u0631\u06cc\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0627\u0633\u062a. <code>padding<\/code> \u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0634\u0645\u0627 \u0645\u0634\u062e\u0635 \u0645\u06cc \u06a9\u0646\u06cc\u062f <code>post<\/code> \u0628\u0631\u0627\u06cc \u0627\u0636\u0627\u0641\u0647 \u06a9\u0631\u062f\u0646 \u0628\u0627\u0644\u0634\u062a\u06a9 \u062f\u0631 \u067e\u0627\u06cc\u0627\u0646 \u062c\u0645\u0644\u0627\u062a.<\/p>\n<p>\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\">padded_sentences = pad_sequences(embedded_sentences, length_long_sentence, padding=<span class=\"hljs-string\">'post'<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(padded_sentences)\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u0628\u0627\u06cc\u062f \u062c\u0645\u0644\u0627\u062a\u06cc \u0628\u0627 padding \u0628\u0628\u06cc\u0646\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">((31 12 31 14  9  0  0)\n (20  3 20 16 18 45 14)\n (16 26 29 14 12  1  0)\n (16 23  0  0  0  0  0)\n (32 41 13 20 18 45 14)\n (15 28 16 43  0  0  0)\n ( 7  9 31 28 31  9  0)\n (14 12 28 46  9  0  0)\n ( 4 22  0  0  0  0  0)\n ( 5  4  9  0  0  0  0)\n (23 46  0  0  0  0  0)\n (14 20 32 14  0  0  0)\n (18  1 26 45 20  9  0)\n (20  9 20  4  0  0  0)\n (18  8 26 34  0  0  0)\n (20 22 12 23  0  0  0))\n<\/code><\/pre>\n<p>\u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0635\u0641\u0631\u0647\u0627 \u0631\u0627 \u062f\u0631 \u0627\u0646\u062a\u0647\u0627\u06cc \u062c\u0645\u0644\u0627\u062a \u067e\u0631 \u0634\u062f\u0647 \u0628\u0628\u06cc\u0646\u06cc\u062f.<\/p>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u0645\u0627 \u0647\u0645\u0647 \u0686\u06cc\u0632\u0647\u0627\u06cc\u06cc \u0631\u0627 \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u06cc\u06a9 \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0627\u062d\u0633\u0627\u0633\u0627\u062a \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u0645\u060c \u062f\u0627\u0631\u06cc\u0645.<\/p>\n<p>\u0645\u0627 \u06cc\u06a9 \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0645\u062a\u0646 \u0628\u0633\u06cc\u0627\u0631 \u0633\u0627\u062f\u0647 \u0628\u0627 \u06cc\u06a9 \u0644\u0627\u06cc\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u0648 \u0628\u062f\u0648\u0646 \u0644\u0627\u06cc\u0647 \u0647\u0627\u06cc \u067e\u0646\u0647\u0627\u0646 \u0627\u06cc\u062c\u0627\u062f \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.  \u0628\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">model = Sequential()\nmodel.add(Embedding(vocab_length, <span class=\"hljs-number\">20<\/span>, input_length=length_long_sentence))\nmodel.add(Flatten())\nmodel.add(Dense(<span class=\"hljs-number\">1<\/span>, activation=<span class=\"hljs-string\">'sigmoid'<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c a \u0631\u0627 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>Sequential<\/code> \u0645\u062f\u0644 \u06a9\u0646\u06cc\u062f \u0648 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f <code>Embedding<\/code> \u0644\u0627\u06cc\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0627\u0648\u0644\u06cc\u0646 \u0644\u0627\u06cc\u0647 \u0628\u0647 \u0645\u062f\u0644.  \u0637\u0648\u0644 \u0648\u0627\u0698\u06af\u0627\u0646 \u062a\u0648\u0633\u0637 \u0639\u0644\u0627\u0645\u062a \u0645\u0634\u062e\u0635 \u0645\u06cc \u0634\u0648\u062f <code>vocab_length<\/code> \u067e\u0627\u0631\u0627\u0645\u062a\u0631.  \u0628\u0639\u062f \u0647\u0631 \u0628\u0631\u062f\u0627\u0631 \u06a9\u0644\u0645\u0647 20 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f \u0648 <code>input_length<\/code> \u0637\u0648\u0644 \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f \u06a9\u0647 7 \u0627\u0633\u062a. \u0628\u0639\u062f\u060c the <code>Embedding<\/code> \u0644\u0627\u06cc\u0647 \u0635\u0627\u0641 \u0645\u06cc \u0634\u0648\u062f \u062a\u0627 \u0628\u062a\u0648\u0627\u0646 \u0645\u0633\u062a\u0642\u06cc\u0645\u0627\u064b \u0628\u0627 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0635\u0644 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.  \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0627\u06cc\u0646 \u06cc\u06a9 \u0645\u0634\u06a9\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0627\u06cc\u0646\u0631\u06cc \u0627\u0633\u062a\u060c \u0645\u0627 \u0627\u0632 \u0622\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>sigmoid<\/code> \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u062a\u0627\u0628\u0639 \u0636\u0631\u0631 \u062f\u0631 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0639\u0645\u0644 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<p>\u062f\u0631 \u0627\u062f\u0627\u0645\u0647 \u0645\u062f\u0644 \u0648 \u0631\u0627 \u06a9\u0627\u0645\u067e\u0627\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u06cc\u0645 print \u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u0645\u0627\u060c \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:<\/p>\n<pre><code class=\"hljs\">model.<span class=\"hljs-built_in\">compile<\/span>(optimizer=<span class=\"hljs-string\">'adam'<\/span>, loss=<span class=\"hljs-string\">'binary_crossentropy'<\/span>, metrics=(<span class=\"hljs-string\">'acc'<\/span>))\n<span class=\"hljs-built_in\">print<\/span>(model.summary())\n<\/code><\/pre>\n<p>\u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u0628\u0647 \u0634\u0631\u062d \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Layer (type)                 Output Shape              Param #\n=================================================================\nembedding_1 (Embedding)      (None, 7, 20)             1000\n_________________________________________________________________\nflatten_1 (Flatten)          (None, 140)               0\n_________________________________________________________________\ndense_1 (Dense)              (None, 1)                 141\n=================================================================\nTotal params: 1,141\nTrainable params: 1,141\nNon-trainable params: 0\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0644\u0627\u06cc\u0647 \u0627\u0648\u0644 \u062f\u0627\u0631\u0627\u06cc 1000 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0642\u0627\u0628\u0644 \u0622\u0645\u0648\u0632\u0634 \u0627\u0633\u062a.  \u0627\u06cc\u0646 \u0628\u0647 \u0627\u06cc\u0646 \u062f\u0644\u06cc\u0644 \u0627\u0633\u062a \u06a9\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u0645\u0627 50 \u0627\u0633\u062a \u0648 \u0647\u0631 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 20 \u0628\u0639\u062f\u06cc \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u0627\u0632 \u0627\u06cc\u0646 \u0631\u0648 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644 \u067e\u0627\u0631\u0627\u0645\u062a\u0631\u0647\u0627\u06cc \u0642\u0627\u0628\u0644 \u0622\u0645\u0648\u0632\u0634 1000 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f. \u0628\u0647 \u0637\u0648\u0631 \u0645\u0634\u0627\u0628\u0647\u060c \u062e\u0631\u0648\u062c\u06cc \u0627\u0632 \u0644\u0627\u06cc\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u0628\u0627 7 \u06a9\u0644\u0645\u0647 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u0647\u0631 \u06a9\u0644\u0645\u0647 \u0628\u0627 \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 20 \u0628\u0639\u062f\u06cc \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0647\u0646\u06af\u0627\u0645\u06cc \u06a9\u0647 \u062e\u0631\u0648\u062c\u06cc \u062f\u0648 \u0628\u0639\u062f\u06cc \u0645\u0633\u0637\u062d \u0645\u06cc \u0634\u0648\u062f\u060c \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 140 \u0628\u0639\u062f\u06cc (7\u00d720) \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u0628\u0631\u062f\u0627\u0631 \u0645\u0633\u0637\u062d \u0645\u0633\u062a\u0642\u06cc\u0645\u0627\u064b \u0628\u0647 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645\u06cc \u06a9\u0647 \u062d\u0627\u0648\u06cc 1 \u0646\u0648\u0631\u0648\u0646 \u0627\u0633\u062a \u0645\u062a\u0635\u0644 \u0627\u0633\u062a.<\/p>\n<p>\u062d\u0627\u0644\u0627 \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0645\u062f\u0644 \u0631\u0627 \u0622\u0645\u0648\u0632\u0634 \u062f\u0647\u06cc\u0645 \u0631\u0648\u06cc \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>fit<\/code> \u0631\u0648\u0634\u060c \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:<\/p>\n<pre><code class=\"hljs\">model.fit(padded_sentences, sentiments, epochs=<span class=\"hljs-number\">100<\/span>, verbose=<span class=\"hljs-number\">1<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06cc\u0646 \u0645\u062f\u0644 \u0628\u0631\u0627\u06cc 100 \u062f\u0648\u0631\u0647 \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u062f \u0634\u062f.<\/p>\n<p>\u0645\u0627 \u0645\u062f\u0644 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0647\u0645\u0627\u0646 \u067e\u06cc\u06a9\u0631\u0647 \u0622\u0645\u0648\u0632\u0634 \u0648 \u0622\u0632\u0645\u0627\u06cc\u0634 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u0639\u0645\u0644\u06a9\u0631\u062f \u0645\u062f\u0644 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627:<\/p>\n<pre><code class=\"hljs\">loss, accuracy = model.evaluate(padded_sentences, sentiments, verbose=<span class=\"hljs-number\">0<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">'Accuracy: %f'<\/span> % (accuracy*<span class=\"hljs-number\">100<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f \u06a9\u0647 \u062f\u0642\u062a \u0645\u062f\u0644 1.00 \u06cc\u0639\u0646\u06cc 100 \u062f\u0631\u0635\u062f \u0627\u0633\u062a.<\/p>\n<p><strong>\u062a\u0648\u062c\u0647 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f<\/strong>: \u062f\u0631 \u0628\u0631\u0646\u0627\u0645\u0647 \u0647\u0627\u06cc \u06a9\u0627\u0631\u0628\u0631\u062f\u06cc \u062f\u0646\u06cc\u0627\u06cc \u0648\u0627\u0642\u0639\u06cc\u060c \u0645\u062c\u0645\u0648\u0639\u0647 \u0647\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0648 \u062a\u0633\u062a \u0628\u0627\u06cc\u062f \u0645\u062a\u0641\u0627\u0648\u062a \u0628\u0627\u0634\u0646\u062f.  \u0647\u0646\u06af\u0627\u0645\u06cc \u06a9\u0647 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0645\u062a\u0646 \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u06cc\u0645\u060c \u0646\u0645\u0648\u0646\u0647 \u0627\u06cc \u0627\u0632 \u0622\u0646 \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f \u0631\u0648\u06cc \u0628\u0631\u062e\u06cc \u0627\u0632 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u062f\u0646\u06cc\u0627\u06cc \u0648\u0627\u0642\u0639\u06cc \u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0622\u06cc\u0646\u062f\u0647.<\/p>\n<h4 id=\"loadingpretrainedwordembeddings\">\u0628\u0627\u0631\u06af\u06cc\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647<\/h4>\n<p>\u062f\u0631 \u0628\u062e\u0634 \u0642\u0628\u0644 \u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0627\u062a \u0633\u0641\u0627\u0631\u0634\u06cc \u0631\u0627 \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u06cc\u0645.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0627\u0632 \u062a\u0639\u0628\u06cc\u0647\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0627\u062a \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647 \u0646\u06cc\u0632 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0686\u0646\u062f\u06cc\u0646 \u0646\u0648\u0639 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634 \u062f\u06cc\u062f\u0647 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f\u060c \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644 \u0645\u0627 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 GloVe \u0627\u0632 Stanford NLP \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f \u0632\u06cc\u0631\u0627 \u0645\u0639\u0631\u0648\u0641 \u062a\u0631\u06cc\u0646 \u0648 \u0631\u0627\u06cc\u062c \u062a\u0631\u06cc\u0646 \u0627\u0633\u062a.  \u06a9\u0644\u0645\u0647 embeddings \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u0627\u06cc\u0646\u062c\u0627 \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0631\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/nlp.stanford.edu\/projects\/glove\/\">\u0627\u06cc\u0646 \u0644\u06cc\u0646\u06a9<\/a>.<\/p>\n<p>\u06a9\u0648\u0686\u06a9\u062a\u0631\u06cc\u0646 \u0641\u0627\u06cc\u0644 &#8220;Glove.6B.zip&#8221; \u0646\u0627\u0645 \u062f\u0627\u0631\u062f.  \u062d\u062c\u0645 \u0641\u0627\u06cc\u0644 822 \u0645\u06af\u0627\u0628\u0627\u06cc\u062a \u0627\u0633\u062a.  \u0627\u06cc\u0646 \u0641\u0627\u06cc\u0644 \u0634\u0627\u0645\u0644 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 50\u060c 100\u060c 200 \u0648 300 \u0628\u0639\u062f\u06cc \u0628\u0631\u0627\u06cc 400 \u0647\u0632\u0627\u0631 \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a.  \u0645\u0627 \u0627\u0632 \u0628\u0631\u062f\u0627\u0631 100 \u0628\u0639\u062f\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.<\/p>\n<p>\u0627\u06cc\u0646 process \u06a9\u0627\u0645\u0644\u0627 \u0645\u0634\u0627\u0628\u0647 \u0627\u0633\u062a  \u0627\u0648\u0644 \u0628\u0627\u06cc\u062f import \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0646\u06cc\u0627\u0632:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> numpy <span class=\"hljs-keyword\">import<\/span> array\n<span class=\"hljs-keyword\">from<\/span> keras.preprocessing.text <span class=\"hljs-keyword\">import<\/span> one_hot\n<span class=\"hljs-keyword\">from<\/span> keras.preprocessing.sequence <span class=\"hljs-keyword\">import<\/span> pad_sequences\n<span class=\"hljs-keyword\">from<\/span> keras.models <span class=\"hljs-keyword\">import<\/span> Sequential\n<span class=\"hljs-keyword\">from<\/span> keras.layers <span class=\"hljs-keyword\">import<\/span> Dense\n<span class=\"hljs-keyword\">from<\/span> keras.layers <span class=\"hljs-keyword\">import<\/span> Flatten\n<span class=\"hljs-keyword\">from<\/span> keras.layers.embeddings <span class=\"hljs-keyword\">import<\/span> Embedding\n<\/code><\/pre>\n<p>\u0628\u0639\u062f\u060c \u0645\u0627 \u0628\u0627\u06cc\u062f \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u062f\u0646\u0628\u0627\u0644 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\">corpus = (\n    \n\n    <span class=\"hljs-string\">'This is an excellent movie'<\/span>,\n    <span class=\"hljs-string\">'The move was fantastic I like it'<\/span>,\n    <span class=\"hljs-string\">'You should watch it is brilliant'<\/span>,\n    <span class=\"hljs-string\">'Exceptionally good'<\/span>,\n    <span class=\"hljs-string\">'Wonderfully directed and executed I like it'<\/span>,\n    <span class=\"hljs-string\">'It'<\/span>s a fantastic series<span class=\"hljs-string\">',\n    '<\/span>Never watched such a brilliant movie<span class=\"hljs-string\">',\n    '<\/span>It <span class=\"hljs-keyword\">is<\/span> a Wonderful movie<span class=\"hljs-string\">',\n\n    # Negative Reviews\n\n    \"horrible acting\",\n    '<\/span>waste of money<span class=\"hljs-string\">',\n    '<\/span>pathetic picture<span class=\"hljs-string\">',\n    '<\/span>It was very boring<span class=\"hljs-string\">',\n    '<\/span>I did <span class=\"hljs-keyword\">not<\/span> like the movie<span class=\"hljs-string\">',\n    '<\/span>The movie was horrible<span class=\"hljs-string\">',\n    '<\/span>I will <span class=\"hljs-keyword\">not<\/span> recommend<span class=\"hljs-string\">',\n    '<\/span>The acting <span class=\"hljs-keyword\">is<\/span> pathetic<span class=\"hljs-string\">'\n)\n<\/span><\/code><\/pre>\n<pre><code class=\"hljs\">sentiments = array((<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">1<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>,<span class=\"hljs-number\">0<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0628\u062e\u0634 \u0622\u062e\u0631 \u0627\u0632 <code>one_hot<\/code> \u062a\u0627\u0628\u0639 \u062a\u0628\u062f\u06cc\u0644 \u0645\u062a\u0646 \u0628\u0647 \u0628\u0631\u062f\u0627\u0631  \u0631\u0648\u0634 \u062f\u06cc\u06af\u0631 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>Tokenizer<\/code> \u062a\u0627\u0628\u0639 \u0627\u0632 <code>keras.preprocessing.text<\/code> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647<\/p>\n<p>\u0634\u0645\u0627 \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u0628\u0627\u06cc\u062f \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0622\u0646 \u0645\u0646\u062a\u0642\u0644 \u06a9\u0646\u06cc\u062f <code>Tokenizer<\/code>&#8216;s <code>fit_on_text<\/code> \u0631\u0648\u0634.<\/p>\n<pre><code class=\"hljs\">word_tokenizer = Tokenizer()\nword_tokenizer.fit_on_texts(corpus)\n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u0628\u0647 \u062f\u0633\u062a \u0622\u0648\u0631\u062f\u0646 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0645\u062a\u0646\u060c \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0637\u0648\u0644 \u0622\u0646 \u0631\u0627 \u0628\u0634\u0645\u0627\u0631\u06cc\u062f <code>word_index<\/code> \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0627\u0632 <code>word_tokenizer<\/code> \u0647\u062f\u0641 &#8211; \u0634\u06cc.  \u0628\u0647 \u06cc\u0627\u062f \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u06a9\u0647 1 \u0631\u0627 \u0628\u0627 \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f.  \u0627\u06cc\u0646 \u0628\u0631\u0627\u06cc \u0630\u062e\u06cc\u0631\u0647 \u0627\u0628\u0639\u0627\u062f \u0628\u0631\u0627\u06cc \u06a9\u0644\u0645\u0627\u062a\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0647\u06cc\u0686 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0627\u06cc \u0627\u0632 \u0642\u0628\u0644 \u0622\u0645\u0648\u0632\u0634 \u062f\u06cc\u062f\u0647 \u0628\u0631\u0627\u06cc \u0622\u0646\u0647\u0627 \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0631\u062f.<\/p>\n<pre><code class=\"hljs\">vocab_length = <span class=\"hljs-built_in\">len<\/span>(word_tokenizer.word_index) + <span class=\"hljs-number\">1<\/span>\n<\/code><\/pre>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u062c\u0645\u0644\u0627\u062a \u0628\u0647 \u0647\u0645\u062a\u0627\u06cc \u0639\u062f\u062f\u06cc \u062e\u0648\u062f\u060c \u0628\u0627 \u0634\u0645\u0627\u0631\u0647 \u062a\u0645\u0627\u0633 \u0628\u06af\u06cc\u0631\u06cc\u062f <code>texts_to_sequences<\/code> \u0639\u0645\u0644\u06a9\u0631\u062f \u0648 \u0622\u0646 \u0631\u0627 \u0628\u0647 \u06a9\u0644 \u0628\u062f\u0646\u0647 \u0645\u0646\u062a\u0642\u0644 \u06a9\u0646\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">embedded_sentences = word_tokenizer.texts_to_sequences(corpus)\n<span class=\"hljs-built_in\">print<\/span>(embedded_sentences)\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u062c\u0645\u0644\u0627\u062a \u0631\u0627 \u0628\u0647 \u0634\u06a9\u0644 \u0639\u062f\u062f\u06cc \u0645\u0634\u0627\u0647\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u062f \u06a9\u0631\u062f:<\/p>\n<pre><code class=\"hljs\">((14, 3, 15, 16, 1), (4, 17, 6, 9, 5, 7, 2), (18, 19, 20, 2, 3, 21), (22, 23), (24, 25, 26, 27, 5, 7, 2), (28, 8, 9, 29), (30, 31, 32, 8, 33, 1), (2, 3, 8, 34, 1), (10, 11), (35, 36, 37), (12, 38), (2, 6, 39, 40), (5, 41, 13, 7, 4, 1), (4, 1, 6, 10), (5, 42, 13, 43), (4, 11, 3, 12))\n<\/code><\/pre>\n<p>\u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u06cc\u0627\u0641\u062a\u0646 \u062a\u0639\u062f\u0627\u062f \u06a9\u0644\u0645\u0627\u062a \u062f\u0631 \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0648 \u0633\u067e\u0633 \u0627\u0639\u0645\u0627\u0644 padding \u0628\u0631\u0627\u06cc \u062c\u0645\u0644\u0627\u062a\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0637\u0648\u0644 \u0647\u0627\u06cc \u06a9\u0648\u062a\u0627\u0647 \u062a\u0631 \u0627\u0632 \u0637\u0648\u0644 \u0637\u0648\u0644\u0627\u0646\u06cc \u062a\u0631\u06cc\u0646 \u062c\u0645\u0644\u0647 \u062f\u0627\u0631\u0646\u062f.<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> nltk.tokenize <span class=\"hljs-keyword\">import<\/span> word_tokenize\n\nword_count = <span class=\"hljs-keyword\">lambda<\/span> sentence: <span class=\"hljs-built_in\">len<\/span>(word_tokenize(sentence))\nlongest_sentence = <span class=\"hljs-built_in\">max<\/span>(corpus, key=word_count)\nlength_long_sentence = <span class=\"hljs-built_in\">len<\/span>(word_tokenize(longest_sentence))\n\npadded_sentences = pad_sequences(embedded_sentences, length_long_sentence, padding=<span class=\"hljs-string\">'post'<\/span>)\n\n<span class=\"hljs-built_in\">print<\/span>(padded_sentences)\n<\/code><\/pre>\n<p>\u062c\u0645\u0644\u0627\u062a \u067e\u0631 \u0634\u062f\u0647 \u0628\u0647 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">((14  3 15 16  1  0  0)\n ( 4 17  6  9  5  7  2)\n (18 19 20  2  3 21  0)\n (22 23  0  0  0  0  0)\n (24 25 26 27  5  7  2)\n (28  8  9 29  0  0  0)\n (30 31 32  8 33  1  0)\n ( 2  3  8 34  1  0  0)\n (10 11  0  0  0  0  0)\n (35 36 37  0  0  0  0)\n (12 38  0  0  0  0  0)\n ( 2  6 39 40  0  0  0)\n ( 5 41 13  7  4  1  0)\n ( 4  1  6 10  0  0  0)\n ( 5 42 13 43  0  0  0)\n ( 4 11  3 12  0  0  0))\n<\/code><\/pre>\n<p>\u0645\u0627 \u062c\u0645\u0644\u0627\u062a \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u062f\u0646\u0628\u0627\u0644\u0647\u200c\u0627\u06cc \u0627\u0632 \u0627\u0639\u062f\u0627\u062f \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0631\u062f\u0647\u200c\u0627\u06cc\u0645.  \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 GloVe \u0648 \u0633\u067e\u0633 \u0627\u06cc\u062c\u0627\u062f \u0645\u0627\u062a\u0631\u06cc\u0633 \u062c\u0627\u0633\u0627\u0632\u06cc \u0645\u0627 \u0627\u0633\u062a \u06a9\u0647 \u062d\u0627\u0648\u06cc \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627 \u0648 \u0645\u0642\u0627\u062f\u06cc\u0631 \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u0622\u0646\u0647\u0627 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\u06cc GloVe \u0627\u0633\u062a.  \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\"><span class=\"hljs-keyword\">from<\/span> numpy <span class=\"hljs-keyword\">import<\/span> array\n<span class=\"hljs-keyword\">from<\/span> numpy <span class=\"hljs-keyword\">import<\/span> asarray\n<span class=\"hljs-keyword\">from<\/span> numpy <span class=\"hljs-keyword\">import<\/span> zeros\n\nembeddings_dictionary = <span class=\"hljs-built_in\">dict<\/span>()\nglove_file = <span class=\"hljs-built_in\">open<\/span>(<span class=\"hljs-string\">'E:\/Datasets\/Word Embeddings\/glove.6B.100d.txt'<\/span>, encoding=<span class=\"hljs-string\">\"utf8\"<\/span>)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u062a\u0639\u0628\u06cc\u0647\u200c\u0647\u0627\u06cc GloVe\u060c \u0686\u0646\u062f \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0631\u0627 \u0646\u06cc\u0632 \u0648\u0627\u0631\u062f \u06a9\u0631\u062f\u06cc\u0645.  \u062f\u0631 \u0628\u062e\u0634 \u0628\u0639\u062f\u06cc \u0634\u0627\u0647\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u0628\u0648\u062f.  \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627\u060c \u062a\u0648\u062c\u0647 \u06a9\u0646\u06cc\u062f \u06a9\u0647 \u0645\u0627 \u0631\u0627 \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u06a9\u0631\u062f\u06cc\u0645 <code>glove.6B.100d.txt<\/code> \u0641\u0627\u06cc\u0644.  \u0627\u06cc\u0646 \u0641\u0627\u06cc\u0644 \u0634\u0627\u0645\u0644 100 \u062a\u0639\u0628\u06cc\u0647 \u06a9\u0644\u0645\u0647 \u0628\u0639\u062f\u06cc \u0627\u0633\u062a.  \u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u06cc\u06a9 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u062e\u0627\u0644\u06cc \u0627\u06cc\u062c\u0627\u062f \u06a9\u0631\u062f\u06cc\u0645 \u06a9\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0645\u0627 \u0631\u0627 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<p>\u0627\u06af\u0631 \u0641\u0627\u06cc\u0644 \u0631\u0627 \u0628\u0627\u0632 \u06a9\u0646\u06cc\u062f\u060c \u062f\u0631 \u0627\u0628\u062a\u062f\u0627\u06cc \u0647\u0631 \u062e\u0637 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f \u06a9\u0647 \u0628\u0627 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc \u0627\u0632 100 \u0639\u062f\u062f \u0647\u0645\u0631\u0627\u0647 \u0627\u0633\u062a.  \u0627\u0639\u062f\u0627\u062f \u0628\u0631\u062f\u0627\u0631 100 \u0628\u0639\u062f\u06cc \u06a9\u0644\u0645\u0647 \u0631\u0627 \u062f\u0631 \u0627\u0628\u062a\u062f\u0627\u06cc \u0647\u0631 \u062e\u0637 \u062a\u0634\u06a9\u06cc\u0644 \u0645\u06cc \u062f\u0647\u0646\u062f.<\/p>\n<p>\u0645\u0627 \u06cc\u06a9 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0627\u06cc\u062c\u0627\u062f \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f \u06a9\u0647 \u062d\u0627\u0648\u06cc \u06a9\u0644\u0645\u0627\u062a \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06a9\u0644\u06cc\u062f \u0648 100 \u0628\u0631\u062f\u0627\u0631 \u0628\u0639\u062f\u06cc \u0645\u0631\u0628\u0648\u0637\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u0642\u0627\u062f\u06cc\u0631\u060c \u062f\u0631 \u0642\u0627\u0644\u0628 \u06cc\u06a9 \u0622\u0631\u0627\u06cc\u0647 \u0628\u0627\u0634\u062f.  \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\"><span class=\"hljs-keyword\">for<\/span> line <span class=\"hljs-keyword\">in<\/span> glove_file:\n    records = line.split()\n    word = records(<span class=\"hljs-number\">0<\/span>)\n    vector_dimensions = asarray(records(<span class=\"hljs-number\">1<\/span>:), dtype=<span class=\"hljs-string\">'float32'<\/span>)\n    embeddings_dictionary (word) = vector_dimensions\n\nglove_file.close()\n<\/code><\/pre>\n<p>\u0644\u063a\u062a \u0646\u0627\u0645\u0647 <code>embeddings_dictionary<\/code> \u0627\u06a9\u0646\u0648\u0646 \u062d\u0627\u0648\u06cc \u06a9\u0644\u0645\u0627\u062a \u0648 \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc GloVe \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u0647\u0645\u0647 \u06a9\u0644\u0645\u0627\u062a \u0627\u0633\u062a.<\/p>\n<p>\u0645\u0627 \u0641\u0642\u0637 \u0628\u0631\u0627\u06cc \u06a9\u0644\u0645\u0627\u062a\u06cc \u06a9\u0647 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u0646\u062f\u060c \u06a9\u0644\u0645\u0647 embeddings \u0631\u0627 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645.  \u0645\u0627 \u06cc\u06a9 \u0622\u0631\u0627\u06cc\u0647 \u062f\u0648 \u0628\u0639\u062f\u06cc NumPy \u0627\u0632 44 \u0631\u062f\u06cc\u0641 (\u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646) \u0631\u062f\u06cc\u0641 \u0648 100 \u0633\u062a\u0648\u0646 \u0627\u06cc\u062c\u0627\u062f \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.  \u0622\u0631\u0627\u06cc\u0647 \u062f\u0631 \u0627\u0628\u062a\u062f\u0627 \u062d\u0627\u0648\u06cc \u0635\u0641\u0631 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.  \u0622\u0631\u0627\u06cc\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u062e\u0648\u0627\u0647\u062f \u0634\u062f <code>embedding_matrix<\/code><\/p>\n<p>\u062f\u0631 \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u060c \u0628\u0627 \u0639\u0628\u0648\u0631 \u0627\u0632 \u0647\u0631 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062e\u0648\u062f \u062a\u06a9\u0631\u0627\u0631 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>word_tokenizer.word_index<\/code> \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u06a9\u0647 \u062d\u0627\u0648\u06cc \u06a9\u0644\u0645\u0627\u062a \u0645\u0627 \u0648 \u0646\u0645\u0627\u06cc\u0647 \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u0622\u0646\u0647\u0627 \u0627\u0633\u062a.<\/p>\n<p>\u0647\u0631 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u06a9\u0644\u06cc\u062f \u0628\u0647 <code>embedding_dictionary<\/code> \u0628\u0631\u0627\u06cc \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u0628\u0631\u062f\u0627\u0631 100 \u0628\u0639\u062f\u06cc \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u06a9\u0644\u0645\u0647.  \u0633\u067e\u0633 \u0628\u0631\u062f\u0627\u0631 100 \u0628\u0639\u062f\u06cc \u062f\u0631 \u0634\u0627\u062e\u0635 \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u0634\u0648\u062f <code>embedding_matrix<\/code>.  \u0628\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">embedding_matrix = zeros((vocab_length, <span class=\"hljs-number\">100<\/span>))\n<span class=\"hljs-keyword\">for<\/span> word, index <span class=\"hljs-keyword\">in<\/span> word_tokenizer.word_index.items():\n    embedding_vector = embeddings_dictionary.get(word)\n    <span class=\"hljs-keyword\">if<\/span> embedding_vector <span class=\"hljs-keyword\">is<\/span> <span class=\"hljs-keyword\">not<\/span> <span class=\"hljs-literal\">None<\/span>:\n        embedding_matrix(index) = embedding_vector\n<\/code><\/pre>\n<p>\u0645\u0627 <code>embedding_matrix<\/code> \u0627\u06a9\u0646\u0648\u0646 \u0634\u0627\u0645\u0644 \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647 \u0628\u0631\u0627\u06cc \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0645\u0627 \u0627\u0633\u062a.<\/p>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u0645\u0627 \u0622\u0645\u0627\u062f\u0647 \u0647\u0633\u062a\u06cc\u0645 \u062a\u0627 \u0645\u062f\u0644 \u0645\u062a\u0648\u0627\u0644\u06cc \u062e\u0648\u062f \u0631\u0627 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645.  \u0628\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">model = Sequential()\nembedding_layer = Embedding(vocab_length, <span class=\"hljs-number\">100<\/span>, weights=(embedding_matrix), input_length=length_long_sentence, trainable=<span class=\"hljs-literal\">False<\/span>)\nmodel.add(embedding_layer)\nmodel.add(Flatten())\nmodel.add(Dense(<span class=\"hljs-number\">1<\/span>, activation=<span class=\"hljs-string\">'sigmoid'<\/span>))\n<\/code><\/pre>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0647 \u062c\u0632 \u0644\u0627\u06cc\u0647 embedding \u062b\u0627\u0628\u062a \u0645\u06cc \u0645\u0627\u0646\u062f.  \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u062f\u0631 \u0644\u0627\u06cc\u0647 embedding\u060c \u0627\u0648\u0644\u06cc\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u0627\u0646\u062f\u0627\u0632\u0647 \u0648\u0627\u0698\u06af\u0627\u0646 \u0627\u0633\u062a.  \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0648\u0645 \u0628\u0639\u062f \u0628\u0631\u062f\u0627\u0631\u06cc \u0628\u0631\u062f\u0627\u0631 \u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u062a.  \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0645\u0627 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647\u200c\u0634\u062f\u0647\u200c\u0627\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645 \u06a9\u0647 \u062d\u0627\u0648\u06cc 100 \u0628\u0631\u062f\u0627\u0631 \u0628\u0639\u062f\u06cc \u0627\u0633\u062a\u060c \u0628\u0639\u062f \u0628\u0631\u062f\u0627\u0631\u06cc \u0631\u0627 \u0631\u0648\u06cc 100 \u0642\u0631\u0627\u0631 \u0645\u06cc\u200c\u062f\u0647\u06cc\u0645.<\/p>\n<p>\u06cc\u06a9\u06cc \u062f\u06cc\u06af\u0631 \u0627\u0632 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627\u06cc \u0628\u0633\u06cc\u0627\u0631 \u0645\u0647\u0645 \u0627\u0632 <code>Embedding()<\/code> \u0644\u0627\u06cc\u0647 \u0627\u06cc \u06a9\u0647 \u062f\u0631 \u0642\u0633\u0645\u062a \u0622\u062e\u0631 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0646\u06a9\u0631\u062f\u06cc\u0645 \u0627\u0633\u062a <code>weights<\/code>.  \u0634\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0645\u0627\u062a\u0631\u06cc\u0633 \u062a\u0639\u0628\u06cc\u0647 \u0634\u062f\u0647 \u0627\u0632 \u0642\u0628\u0644 \u0622\u0645\u0648\u0632\u0634 \u062f\u06cc\u062f\u0647 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0632\u0646 \u0647\u0627\u06cc \u067e\u06cc\u0634 \u0641\u0631\u0636 \u062f\u0631 \u0627\u062e\u062a\u06cc\u0627\u0631 \u0642\u0631\u0627\u0631 \u062f\u0647\u06cc\u062f <code>weights<\/code> \u067e\u0627\u0631\u0627\u0645\u062a\u0631.  \u0648 \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0645\u0627 \u0644\u0627\u06cc\u0647 embedding \u0631\u0627 \u0622\u0645\u0648\u0632\u0634 \u0646\u0645\u06cc \u062f\u0647\u06cc\u0645\u060c <code>trainable<\/code> \u0648\u06cc\u0698\u06af\u06cc \u062a\u0646\u0638\u06cc\u0645 \u0634\u062f\u0647 \u0627\u0633\u062a <code>False<\/code>.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0645\u062f\u0644 \u062e\u0648\u062f \u0631\u0627 \u062c\u0645\u0639 \u0622\u0648\u0631\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u062e\u0648\u062f \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">model.<span class=\"hljs-built_in\">compile<\/span>(optimizer=<span class=\"hljs-string\">'adam'<\/span>, loss=<span class=\"hljs-string\">'binary_crossentropy'<\/span>, metrics=(<span class=\"hljs-string\">'acc'<\/span>))\n<span class=\"hljs-built_in\">print<\/span>(model.summary())\n<\/code><\/pre>\n<p>\u0645\u0627 \u062f\u0648\u0628\u0627\u0631\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>adam<\/code> \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0628\u0647\u06cc\u0646\u0647 \u0633\u0627\u0632 \u0628\u0631\u0627\u06cc \u0628\u0647 \u062d\u062f\u0627\u0642\u0644 \u0631\u0633\u0627\u0646\u062f\u0646 \u0636\u0631\u0631.  \u062a\u0627\u0628\u0639 \u0636\u0631\u0631 \u0645\u0648\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0633\u062a <code>binary_crossentropy<\/code>.  \u0648 \u0645\u0627 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645 \u0646\u062a\u0627\u06cc\u062c \u0631\u0627 \u062f\u0631 \u0642\u0627\u0644\u0628 \u062f\u0642\u062a \u0628\u0628\u06cc\u0646\u06cc\u0645 <code>acc<\/code> \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u0642\u062f\u0627\u0631 \u0627\u0631\u0633\u0627\u0644 \u0634\u062f\u0647 \u0627\u0633\u062a <code>metrics<\/code> \u0635\u0641\u062a.<\/p>\n<p>\u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u0628\u0647 \u0634\u0631\u062d \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Layer (type)                 Output Shape              Param #\n=================================================================\nembedding_1 (Embedding)      (None, 7, 100)            4400\n_________________________________________________________________\nflatten_1 (Flatten)          (None, 700)               0\n_________________________________________________________________\ndense_1 (Dense)              (None, 1)                 701\n=================================================================\nTotal params: 5,101\nTrainable params: 701\nNon-trainable params: 4,400\n_________________________________________________________________\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0645\u0627 44 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u0648\u0627\u0698\u06af\u0627\u0646 \u062e\u0648\u062f \u062f\u0627\u0631\u06cc\u0645 \u0648 \u0647\u0631 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0635\u0648\u0631\u062a \u06cc\u06a9 \u0628\u0631\u062f\u0627\u0631 100 \u0628\u0639\u062f\u06cc \u0646\u0645\u0627\u06cc\u0634 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f\u060c \u062a\u0639\u062f\u0627\u062f \u067e\u0627\u0631\u0627\u0645\u062a\u0631\u0647\u0627\u06cc \u0644\u0627\u06cc\u0647 embedding \u0628\u0631\u0627\u0628\u0631 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f. <code>44 x 100 = 4400<\/code>.  \u062e\u0631\u0648\u062c\u06cc \u0644\u0627\u06cc\u0647 embedding \u06cc\u06a9 \u0648\u06a9\u062a\u0648\u0631 \u062f\u0648 \u0628\u0639\u062f\u06cc \u0628\u0627 7 \u0631\u062f\u06cc\u0641 (1 \u0628\u0631\u0627\u06cc \u0647\u0631 \u06a9\u0644\u0645\u0647 \u062f\u0631 \u062c\u0645\u0644\u0647) \u0648 100 \u0633\u062a\u0648\u0646 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.  \u062e\u0631\u0648\u062c\u06cc \u0627\u0632 \u0644\u0627\u06cc\u0647 \u062a\u0639\u0628\u06cc\u0647 \u0634\u062f\u0647 \u0635\u0627\u0641 \u0645\u06cc \u0634\u0648\u062f \u062a\u0627 \u0628\u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u0628\u0627 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0627\u0632 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0628\u0631\u0627\u06cc \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">model.fit(padded_sentences, sentiments, epochs=<span class=\"hljs-number\">100<\/span>, verbose=<span class=\"hljs-number\">1<\/span>)\n<\/code><\/pre>\n<p>\u067e\u0633 \u0627\u0632 \u0622\u0645\u0648\u0632\u0634 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645\u060c \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u0639\u0645\u0644\u06a9\u0631\u062f \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">loss, accuracy = model.evaluate(padded_sentences, sentiments, verbose=<span class=\"hljs-number\">0<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">'Accuracy: %f'<\/span> % (accuracy*<span class=\"hljs-number\">100<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u0628\u0627\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u062f\u0642\u062a 1000 \u06cc\u0639\u0646\u06cc 100 \u062f\u0631\u0635\u062f \u0627\u0633\u062a.<\/p>\n<h3 id=\"wordembeddingswithkerasfunctionalapi\"><span class=\"ez-toc-section\" id=\"%d8%ac%d8%a7%d8%b3%d8%a7%d8%b2%db%8c_%da%a9%d9%84%d9%85%d9%87_%d8%a8%d8%a7_keras_functional_api\"><\/span>\u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 Keras Functional API<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u062f\u0631 \u0628\u062e\u0634 \u0622\u062e\u0631\u060c \u062f\u06cc\u062f\u06cc\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0628\u0627 API \u0645\u062a\u0648\u0627\u0644\u06cc Keras \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.  \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 API \u0645\u062a\u0648\u0627\u0644\u06cc \u0646\u0642\u0637\u0647 \u0634\u0631\u0648\u0639 \u062e\u0648\u0628\u06cc \u0628\u0631\u0627\u06cc \u0645\u0628\u062a\u062f\u06cc\u0627\u0646 \u0627\u0633\u062a\u060c \u0632\u06cc\u0631\u0627 \u0628\u0647 \u0634\u0645\u0627 \u0627\u062c\u0627\u0632\u0647 \u0645\u06cc \u062f\u0647\u062f \u062a\u0627 \u0628\u0647 \u0633\u0631\u0639\u062a \u0645\u062f\u0644 \u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f\u060c \u062f\u0627\u0646\u0633\u062a\u0646 \u0631\u0648\u0634 \u0639\u0645\u0644\u06a9\u0631\u062f Keras Functional API \u0628\u0633\u06cc\u0627\u0631 \u0645\u0647\u0645 \u0627\u0633\u062a.  \u0627\u06a9\u062b\u0631 \u0645\u062f\u0644 \u0647\u0627\u06cc \u067e\u06cc\u0634\u0631\u0641\u062a\u0647 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u06a9\u0647 \u0634\u0627\u0645\u0644 \u0648\u0631\u0648\u062f\u06cc \u0647\u0627 \u0648 \u062e\u0631\u0648\u062c\u06cc \u0647\u0627\u06cc \u0645\u062a\u0639\u062f\u062f \u0647\u0633\u062a\u0646\u062f \u0627\u0632 Functional API \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u0646\u062f.<\/p>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0628\u062e\u0634\u060c \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u06cc\u06a9 \u0644\u0627\u06cc\u0647 embedding \u0631\u0627 \u0628\u0627 Keras Functional API \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0628\u0642\u06cc\u0647 \u0641\u06cc\u0644\u0645\u0646\u0627\u0645\u0647 \u0645\u0627\u0646\u0646\u062f \u0642\u0633\u0645\u062a \u0642\u0628\u0644\u06cc \u0628\u0627\u0642\u06cc \u0645\u06cc \u0645\u0627\u0646\u062f.  \u062a\u0646\u0647\u0627 \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0631 \u062a\u0648\u0633\u0639\u0647 \u06cc\u06a9 \u0645\u062f\u0644 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0647\u0645\u0627\u0646 \u0645\u062f\u0644 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0631\u0627 \u06a9\u0647 \u062f\u0631 \u0628\u062e\u0634 \u0622\u062e\u0631 \u0628\u0627 Keras Functional API \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0631\u062f\u06cc\u0645\u060c \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> keras.models <span class=\"hljs-keyword\">import<\/span> Model\n<span class=\"hljs-keyword\">from<\/span> keras.layers <span class=\"hljs-keyword\">import<\/span> Input\n\ndeep_inputs = Input(shape=(length_long_sentence,))\nembedding = Embedding(vocab_length, <span class=\"hljs-number\">100<\/span>, weights=(embedding_matrix), input_length=length_long_sentence, trainable=<span class=\"hljs-literal\">False<\/span>)(deep_inputs) \nflatten = Flatten()(embedding)\nhidden = Dense(<span class=\"hljs-number\">1<\/span>, activation=<span class=\"hljs-string\">'sigmoid'<\/span>)(flatten)\nmodel = Model(inputs=deep_inputs, outputs=hidden)\n<\/code><\/pre>\n<p>\u062f\u0631 Keras Functional API\u060c \u0628\u0627\u06cc\u062f \u0644\u0627\u06cc\u0647 \u0648\u0631\u0648\u062f\u06cc \u0631\u0627 \u0628\u0647 \u0637\u0648\u0631 \u062c\u062f\u0627\u06af\u0627\u0646\u0647 \u0642\u0628\u0644 \u0627\u0632 \u0644\u0627\u06cc\u0647 embedding \u062a\u0639\u0631\u06cc\u0641 \u06a9\u0646\u06cc\u062f.  \u062f\u0631 \u0644\u0627\u06cc\u0647 \u0648\u0631\u0648\u062f\u06cc \u0628\u0627\u06cc\u062f \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u0637\u0648\u0644 \u0628\u0631\u062f\u0627\u0631 \u0648\u0631\u0648\u062f\u06cc \u0631\u0627 \u0631\u062f \u06a9\u0646\u06cc\u062f.  \u0628\u0631\u0627\u06cc \u062a\u0639\u06cc\u06cc\u0646 \u0644\u0627\u06cc\u0647 \u0642\u0628\u0644\u06cc \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u0644\u0627\u06cc\u0647 \u0628\u0639\u062f\u06cc\u060c \u0644\u0627\u06cc\u0647 \u0642\u0628\u0644\u06cc \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0631 \u062f\u0627\u062e\u0644 \u067e\u0631\u0627\u0646\u062a\u0632\u060c \u062f\u0631 \u0627\u0646\u062a\u0647\u0627\u06cc \u0644\u0627\u06cc\u0647 \u0628\u0639\u062f\u06cc \u0627\u0631\u0633\u0627\u0644 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0622\u0646 \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u062f <code>deep_inputs<\/code> \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u067e\u0627\u0631\u0627\u0645\u062a\u0631 \u062f\u0631 \u0627\u0646\u062a\u0647\u0627\u06cc \u0644\u0627\u06cc\u0647 embedding \u0627\u0631\u0633\u0627\u0644 \u0645\u06cc \u0634\u0648\u062f.  \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062a\u0631\u062a\u06cc\u0628\u060c <code>embedding<\/code> \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u062f\u0631 \u067e\u0627\u06cc\u0627\u0646 \u0627\u0631\u0633\u0627\u0644 \u0645\u06cc \u0634\u0648\u062f <code>Flatten()<\/code> \u0644\u0627\u06cc\u0647 \u0648 \u063a\u06cc\u0631\u0647 \u0631\u0648\u06cc.<\/p>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u062f\u0631 <code>Model()<\/code>\u060c \u0628\u0627\u06cc\u062f \u0644\u0627\u06cc\u0647 \u0648\u0631\u0648\u062f\u06cc \u0648 \u0644\u0627\u06cc\u0647 \u062e\u0631\u0648\u062c\u06cc \u0646\u0647\u0627\u06cc\u06cc \u0631\u0627 \u0631\u062f \u06a9\u0646\u06cc\u062f.<\/p>\n<p>\u062d\u0627\u0644 \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0645\u062f\u0644 \u0631\u0627 \u062c\u0645\u0639 \u0622\u0648\u0631\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0646\u06af\u0627\u0647\u06cc \u0628\u0647 \u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u0628\u06cc\u0646\u062f\u0627\u0632\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\">model.<span class=\"hljs-built_in\">compile<\/span>(optimizer=<span class=\"hljs-string\">'adam'<\/span>, loss=<span class=\"hljs-string\">'binary_crossentropy'<\/span>, metrics=(<span class=\"hljs-string\">'acc'<\/span>))\n<span class=\"hljs-built_in\">print<\/span>(model.summary())\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Layer (type)                 Output Shape              Param #\n=================================================================\ninput_1 (InputLayer)         (None, 7)                 0\n_________________________________________________________________\nembedding_1 (Embedding)      (None, 7, 100)            4400\n_________________________________________________________________\nflatten_1 (Flatten)          (None, 700)               0\n_________________________________________________________________\ndense_1 (Dense)              (None, 1)                 701\n=================================================================\nTotal params: 5,101\nTrainable params: 701\nNon-trainable params: 4,400\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0644\u0627\u06cc\u0647 \u0648\u0631\u0648\u062f\u06cc \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0644\u0627\u06cc\u0647 \u062c\u062f\u0627\u06af\u0627\u0646\u0647 \u0642\u0628\u0644 \u0627\u0632 \u0644\u0627\u06cc\u0647 embedding \u0628\u0628\u06cc\u0646\u06cc\u062f.  \u0628\u0642\u06cc\u0647 \u0645\u062f\u0644 \u0647\u0627 \u0628\u0647 \u0647\u0645\u0627\u0646 \u0634\u06a9\u0644 \u0628\u0627\u0642\u06cc \u0645\u06cc \u0645\u0627\u0646\u0646\u062f.<\/p>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c process \u0628\u0631\u0627\u06cc \u0628\u0631\u0627\u0632\u0634 \u0648 \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u0645\u062f\u0644 \u0645\u0634\u0627\u0628\u0647 \u0645\u062f\u0644 \u0645\u0648\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062f\u0631 Sequential API \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">model.fit(padded_sentences, sentiments, epochs=<span class=\"hljs-number\">100<\/span>, verbose=<span class=\"hljs-number\">1<\/span>)\nloss, accuracy = model.evaluate(padded_sentences, sentiments, verbose=<span class=\"hljs-number\">0<\/span>)\n\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">'Accuracy: %f'<\/span> % (accuracy*<span class=\"hljs-number\">100<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u062f\u0642\u062a 1000 \u06cc\u0639\u0646\u06cc 100 \u062f\u0631\u0635\u062f \u0631\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u062f \u06a9\u0631\u062f.<\/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>\u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u0645\u062f\u0644 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642\u060c \u0628\u0627\u06cc\u062f \u0645\u062a\u0646 \u0631\u0627 \u0628\u0647 \u0639\u062f\u062f \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0628\u0631 \u062e\u0644\u0627\u0641 \u0645\u062f\u0644\u200c\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0645\u0627\u0634\u06cc\u0646\u06cc\u060c \u0639\u0628\u0648\u0631 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u067e\u0631\u0627\u06a9\u0646\u062f\u0647 \u062f\u0631 \u0627\u0646\u062f\u0627\u0632\u0647\u200c\u0647\u0627\u06cc \u0628\u0632\u0631\u06af \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u062a\u0627 \u062d\u062f \u0632\u06cc\u0627\u062f\u06cc \u0628\u0631 \u0645\u062f\u0644\u200c\u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u062a\u0623\u062b\u06cc\u0631 \u0628\u06af\u0630\u0627\u0631\u062f.  \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646\u060c \u0628\u0627\u06cc\u062f \u0645\u062a\u0646 \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u062a\u0631\u0627\u06a9\u0645 \u06a9\u0648\u0686\u06a9 \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0645\u0627 \u06a9\u0645\u06a9 \u0645\u06cc \u06a9\u0646\u062f \u0645\u062a\u0646 \u0631\u0627 \u0628\u0647 \u0628\u0631\u062f\u0627\u0631\u0647\u0627\u06cc \u0645\u062a\u0631\u0627\u06a9\u0645 \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u062f\u06cc\u062f\u06cc\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 Keras \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u06a9\u0631\u062f.  \u0645\u0627 \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0633\u0641\u0627\u0631\u0634\u06cc \u0631\u0627 \u067e\u06cc\u0627\u062f\u0647\u200c\u0633\u0627\u0632\u06cc \u06a9\u0631\u062f\u06cc\u0645 \u0648 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0627\u0632 \u062c\u0627\u0633\u0627\u0632\u06cc\u200c\u0647\u0627\u06cc \u06a9\u0644\u0645\u0647 \u0627\u0632 \u067e\u06cc\u0634 \u0622\u0645\u0648\u0632\u0634\u200c\u062f\u06cc\u062f\u0647 \u0628\u0631\u0627\u06cc \u062d\u0644 \u0648\u0638\u0627\u06cc\u0641 \u0637\u0628\u0642\u0647\u200c\u0628\u0646\u062f\u06cc \u0633\u0627\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f\u06cc\u0645.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0631\u0648\u0634 \u067e\u06cc\u0627\u062f\u0647\u200c\u0633\u0627\u0632\u06cc \u062c\u0627\u0633\u0627\u0632\u06cc \u06a9\u0644\u0645\u0647 \u0628\u0627 Keras Functional API \u0631\u0627 \u0646\u06cc\u0632 \u062f\u06cc\u062f\u06cc\u0645.<\/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 1403-01-21 10:51:03<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;16152&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;Python for NLP: Word Embeddings for Deep Learning \u062f\u0631 Keras&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\"> 14<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span>\u0627\u06cc\u0646 \u0634\u0627\u0646\u0632\u062f\u0647\u0645\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0632 \u0633\u0631\u06cc \u0645\u0642\u0627\u0644\u0627\u062a \u0645\u0646 \u0627\u0633\u062a \u0631\u0648\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc NLP. \u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0642\u0628\u0644\u06cc \u062e\u0648\u062f \u062a\u0648\u0636\u06cc\u062d \u062f\u0627\u062f\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0632 \u062a\u06a9\u0646\u06cc\u06a9 N-Grams \u0628\u0631\u0627\u06cc \u062a\u0648\u0633\u0639\u0647 \u06cc\u06a9 \u067e\u0631\u06a9\u0646\u0646\u062f\u0647 \u0645\u062a\u0646 \u062e\u0648\u062f\u06a9\u0627\u0631 \u0633\u0627\u062f\u0647 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f. \u0645\u062f\u0644 N-Gram \u0627\u0633\u0627\u0633\u0627\u064b \u0631\u0627\u0647\u06cc \u0628\u0631\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0639\u062f\u062f\u06cc \u0627\u0633\u062a \u062a\u0627 \u0628\u062a\u0648\u0627\u0646 \u0627\u0632 \u0622\u0646 \u062a\u0648\u0633\u0637 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 [&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],"tags":[],"class_list":["post-16152","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-python","category-programming"],"acf":[],"_links":{"self":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16152","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=16152"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16152\/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=16152"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=16152"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=16152"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}