{"id":16373,"date":"2024-01-24T06:17:12","date_gmt":"2024-01-24T02:47:12","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/"},"modified":"2024-01-24T06:17:12","modified_gmt":"2024-01-24T02:47:12","slug":"python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/","title":{"rendered":"Python \u0628\u0631\u0627\u06cc NLP: Tokenization\u060c Stemming \u0648 Lemmatization \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 SpaCy"},"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-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d9%85%d8%b9%d8%b1%d9%81%db%8c_spacy\" >\u0645\u0639\u0631\u0641\u06cc SpaCy<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d9%86%d8%b5%d8%a8_spacy\" >\u0646\u0635\u0628 SpaCy<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%b9%d9%85%d9%84%da%a9%d8%b1%d8%af_%d9%be%d8%a7%db%8c%d9%87\" >\u0639\u0645\u0644\u06a9\u0631\u062f \u067e\u0627\u06cc\u0647<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%aa%d9%88%da%a9%d9%86_%d8%b3%d8%a7%d8%b2%db%8c\" >\u062a\u0648\u06a9\u0646 \u0633\u0627\u0632\u06cc<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%b4%d9%86%d8%a7%d8%b3%d8%a7%db%8c%db%8c_%d9%85%d9%88%d8%ac%d9%88%d8%af%db%8c%d8%aa_%d9%87%d8%a7\" >\u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0647\u0627<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%aa%d8%b4%d8%ae%db%8c%d8%b5_%d8%a7%d8%b3%d9%85_%d9%87%d8%a7\" >\u062a\u0634\u062e\u06cc\u0635 \u0627\u0633\u0645 \u0647\u0627<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%b3%d8%a7%d9%82%d9%87\" >\u0633\u0627\u0642\u0647<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d9%be%d9%88%d8%b1%d8%aa%d8%b1_%d8%a7%d8%b3%d8%aa%d9%85%d8%b1\" >\u067e\u0648\u0631\u062a\u0631 \u0627\u0633\u062a\u0645\u0631<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%d8%a7%d8%b3%d8%aa%d9%85%d8%b1_%da%af%d9%84%d9%88%d9%84%d9%87_%d8%a8%d8%b1%d9%81%db%8c\" >\u0627\u0633\u062a\u0645\u0631 \u06af\u0644\u0648\u0644\u0647 \u0628\u0631\u0641\u06cc<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#lemmatization\" >Lemmatization<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/rasanegaar.com\/blog\/python-%d8%a8%d8%b1%d8%a7%db%8c-nlp-tokenization%d8%8c-stemming-%d9%88-lemmatization-%d8%a8%d8%a7-%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87-spacy\/#%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\"> 8<\/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>\u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0642\u0628\u0644\u06cc \u0628\u062d\u062b \u062e\u0648\u062f \u0631\u0627 \u062f\u0631 \u0645\u0648\u0631\u062f \u0631\u0648\u0634 \u0627\u0646\u062c\u0627\u0645 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc \u0628\u0627 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0634\u0631\u0648\u0639 \u06a9\u0631\u062f\u06cc\u0645.  \u0631\u0648\u0634 \u062e\u0648\u0627\u0646\u062f\u0646 \u0648 \u0646\u0648\u0634\u062a\u0646 \u0641\u0627\u06cc\u0644 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0648 PDF \u0631\u0627 \u062f\u06cc\u062f\u06cc\u0645.  \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647\u060c \u0645\u0627 \u0634\u0631\u0648\u0639 \u0628\u0647 \u06a9\u0627\u0631 \u0628\u0627 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/spacy.io\/\">\u0641\u0636\u0627\u06cc\u06cc<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0686\u0646\u062f \u06a9\u0627\u0631 \u0627\u0633\u0627\u0633\u06cc NLP \u0645\u0627\u0646\u0646\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Lexical_analysis#Tokenization\">\u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc<\/a>\u060c <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/nlp.stanford.edu\/IR-book\/html\/htmledition\/stemming-and-lemmatization-1.html\">\u0631\u06cc\u0634\u0647 \u06cc\u0627\u0628\u06cc \u0648 \u0631\u06cc\u0634\u0647 \u06cc\u0627\u0628\u06cc<\/a>.<\/p>\n<h2 id=\"introductiontospacy\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%b9%d8%b1%d9%81%db%8c_spacy\"><\/span>\u0645\u0639\u0631\u0641\u06cc SpaCy<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 spaCy \u06cc\u06a9\u06cc \u0627\u0632 \u0645\u062d\u0628\u0648\u0628 \u062a\u0631\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc NLP \u062f\u0631 \u06a9\u0646\u0627\u0631 NLTK \u0627\u0633\u062a.  \u062a\u0641\u0627\u0648\u062a \u0627\u0633\u0627\u0633\u06cc \u0628\u06cc\u0646 \u0627\u06cc\u0646 \u062f\u0648 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u062f\u0631 \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u0627\u0633\u062a \u06a9\u0647 NLTK \u0634\u0627\u0645\u0644 \u0637\u06cc\u0641 \u06af\u0633\u062a\u0631\u062f\u0647 \u0627\u06cc \u0627\u0632 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627 \u0628\u0631\u0627\u06cc \u062d\u0644 \u06cc\u06a9 \u0645\u0633\u0626\u0644\u0647 \u0627\u0633\u062a \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 spaCy \u062a\u0646\u0647\u0627 \u0634\u0627\u0645\u0644 \u06cc\u06a9 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0627\u0633\u062a\u060c \u0627\u0645\u0627 \u0628\u0647\u062a\u0631\u06cc\u0646 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0628\u0631\u0627\u06cc \u062d\u0644 \u06cc\u06a9 \u0645\u0633\u0626\u0644\u0647.<\/p>\n<p>NLTK \u062f\u0631 \u0633\u0627\u0644 2001 \u0645\u0646\u062a\u0634\u0631 \u0634\u062f \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 spaCy \u0646\u0633\u0628\u062a\u0627 \u062c\u062f\u06cc\u062f \u0627\u0633\u062a \u0648 \u062f\u0631 \u0633\u0627\u0644 2015 \u062a\u0648\u0633\u0639\u0647 \u06cc\u0627\u0641\u062a\u0647 \u0627\u0633\u062a. \u062f\u0631 \u0627\u06cc\u0646 \u0633\u0631\u06cc \u0627\u0632 \u0645\u0642\u0627\u0644\u0627\u062a \u0631\u0648\u06cc NLP\u060c \u0645\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0628\u0627 spaCy \u0633\u0631 \u0648 \u06a9\u0627\u0631 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u0627\u0634\u062a\u060c \u0628\u0647 \u062f\u0644\u06cc\u0644 \u0645\u0627\u0647\u06cc\u062a \u0647\u0646\u0631\u06cc \u0622\u0646.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0647\u0646\u06af\u0627\u0645\u06cc \u06a9\u0647 \u0627\u0646\u062c\u0627\u0645 \u06cc\u06a9 \u06a9\u0627\u0631 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 NLTK \u0628\u0647 \u062c\u0627\u06cc spaCy \u0622\u0633\u0627\u0646 \u062a\u0631 \u0628\u0627\u0634\u062f\u060c NLTK \u0631\u0627 \u0646\u06cc\u0632 \u0644\u0645\u0633 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.<\/p>\n<h3 id=\"installingspacy\"><span class=\"ez-toc-section\" id=\"%d9%86%d8%b5%d8%a8_spacy\"><\/span>\u0646\u0635\u0628 SpaCy<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0627\u06af\u0631 \u0627\u0632 pip \u0646\u0635\u0628 \u06a9\u0646\u0646\u062f\u0647 \u0628\u0631\u0627\u06cc \u0646\u0635\u0628 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646\u060c \u0628\u0647 \u062e\u0637 \u0641\u0631\u0645\u0627\u0646 \u0628\u0631\u0648\u06cc\u062f \u0648 \u0639\u0628\u0627\u0631\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">$ pip install -U spacy\n<\/code><\/pre>\n<p>\u062f\u0631 \u063a\u06cc\u0631 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u0627\u06af\u0631 \u0627\u0632 Anaconda \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u062f\u060c \u0628\u0627\u06cc\u062f \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0631\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc \u0627\u0639\u0644\u0627\u0646 \u0622\u0646\u0627\u06a9\u0648\u0646\u062f\u0627:<\/p>\n<pre><code class=\"hljs\">$ conda install -c conda-forge spacy\n<\/code><\/pre>\n<p>\u067e\u0633 \u0627\u0632 \u062f\u0627\u0646\u0644\u0648\u062f \u0648 \u0646\u0635\u0628 spaCy\u060c \u06af\u0627\u0645 \u0628\u0639\u062f\u06cc \u062f\u0627\u0646\u0644\u0648\u062f \u0645\u062f\u0644 \u0632\u0628\u0627\u0646 \u0627\u0633\u062a.  \u0645\u0627 \u0627\u0632 \u0645\u062f\u0644 \u0632\u0628\u0627\u0646 \u0627\u0646\u06af\u0644\u06cc\u0633\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.  \u0627\u0632 \u0645\u062f\u0644 \u0632\u0628\u0627\u0646 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u0646\u0648\u0627\u0639 \u0648\u0638\u0627\u06cc\u0641 NLP \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f \u06a9\u0647 \u062f\u0631 \u0628\u062e\u0634 \u0628\u0639\u062f\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f.<\/p>\n<p>\u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0645\u062f\u0644 \u0632\u0628\u0627\u0646 \u0631\u0627 \u062f\u0627\u0646\u0644\u0648\u062f \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">$ python -m spacy download en\n<\/code><\/pre>\n<h3 id=\"basicfunctionality\"><span class=\"ez-toc-section\" id=\"%d8%b9%d9%85%d9%84%da%a9%d8%b1%d8%af_%d9%be%d8%a7%db%8c%d9%87\"><\/span>\u0639\u0645\u0644\u06a9\u0631\u062f \u067e\u0627\u06cc\u0647<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0642\u0628\u0644 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0639\u0645\u06cc\u0642\u200c\u062a\u0631 \u0628\u0647 \u062a\u0648\u0627\u0628\u0639 \u0645\u062e\u062a\u0644\u0641 spaCy \u0628\u067e\u0631\u062f\u0627\u0632\u06cc\u0645\u060c \u0627\u062c\u0627\u0632\u0647 \u062f\u0647\u06cc\u062f \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0631\u0648\u0634 \u06a9\u0627\u0631 \u0628\u0627 \u0622\u0646 \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u0645.<\/p>\n<p>\u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0627\u0648\u0644\u06cc\u0646 \u0642\u062f\u0645\u060c \u0634\u0645\u0627 \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u062f import \u0631\u0627 <code>spacy<\/code> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0647 \u0634\u0631\u062d \u0632\u06cc\u0631<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> spacy\n<\/code><\/pre>\n<p>\u0628\u0639\u062f\u060c \u0628\u0627\u06cc\u062f \u0645\u062f\u0644 \u0632\u0628\u0627\u0646 spaCy \u0631\u0627 \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<pre><code class=\"hljs\">sp = spacy.load(<span class=\"hljs-string\">'en_core_web_sm'<\/span>)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u0645\u0627 \u0627\u0632 <code>load<\/code> \u062a\u0627\u0628\u0639 \u0627\u0632 <code>spacy<\/code> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0631\u0627\u06cc \u0628\u0627\u0631\u06af\u0630\u0627\u0631\u06cc \u0645\u062f\u0644 \u0627\u0635\u0644\u06cc \u0632\u0628\u0627\u0646 \u0627\u0646\u06af\u0644\u06cc\u0633\u06cc.  \u0645\u062f\u0644 \u062f\u0631 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u0634\u0648\u062f <code>sp<\/code> \u0645\u062a\u063a\u06cc\u0631.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u06a9\u0646\u0648\u0646 \u06cc\u06a9 \u0633\u0646\u062f \u06a9\u0648\u0686\u06a9 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u06cc\u0646 \u0645\u062f\u0644 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645.  \u06cc\u06a9 \u0633\u0646\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u06cc\u0627 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u06cc \u0627\u0632 \u062c\u0645\u0644\u0627\u062a \u0628\u0627\u0634\u062f \u0648 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0637\u0648\u0644 \u0646\u0627\u0645\u062d\u062f\u0648\u062f\u06cc \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u062f.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u06cc\u06a9 \u0633\u0646\u062f spaCy \u0633\u0627\u062f\u0647 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<pre><code class=\"hljs\">sentence = sp(<span class=\"hljs-string\">u'Manchester United is looking to sign a forward for $90 million'<\/span>)\n<\/code><\/pre>\n<p>\u0648\u0642\u062a\u06cc \u0633\u0646\u062f\u06cc \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0645\u062f\u0644 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc\u200c\u0634\u0648\u062f\u060c spaCy \u0628\u0647\u200c\u0637\u0648\u0631 \u062e\u0648\u062f\u06a9\u0627\u0631 \u0633\u0646\u062f \u0634\u0645\u0627 \u0631\u0627 \u0628\u0647 \u062a\u0648\u06a9\u0646\u200c\u0647\u0627 \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc\u200c\u06a9\u0646\u062f.<\/p>\n<p>\u06cc\u06a9 \u0646\u0634\u0627\u0646\u0647 \u0635\u0631\u0641\u0627\u064b \u0628\u0647 \u0628\u062e\u0634\u06cc \u0627\u0632 \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u06a9\u0647 \u062f\u0627\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u06cc \u0645\u0639\u0646\u0627\u06cc\u06cc \u0627\u0633\u062a \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0686\u0647 \u0646\u0634\u0627\u0646\u0647 \u0647\u0627\u06cc\u06cc \u062f\u0631 \u0633\u0646\u062f \u062e\u0648\u062f \u062f\u0627\u0631\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence:\n    <span class=\"hljs-built_in\">print<\/span>(word.text)\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Manchester\nUnited\nis\nlooking\nto\nsign\na\nforward\nfor\n$\n90\nmillion\n<\/code><\/pre>\n<p>\u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0645\u0627 \u0646\u0634\u0627\u0646\u0647 \u0647\u0627\u06cc \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u0633\u0646\u062f \u062e\u0648\u062f \u062f\u0627\u0631\u06cc\u0645.  \u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0628\u0628\u06cc\u0646\u06cc\u0645 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Part_of_speech\">\u0628\u062e\u0634 \u0647\u0627\u06cc\u06cc \u0627\u0632 \u0633\u062e\u0646\u0631\u0627\u0646\u06cc<\/a> \u0647\u0631 \u06cc\u06a9 \u0627\u0632 \u0627\u06cc\u0646 \u0646\u0634\u0627\u0646\u0647 \u0647\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>.pos_<\/code> \u0648\u06cc\u0698\u06af\u06cc \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u062f\u0631 \u0632\u06cc\u0631:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence:\n    <span class=\"hljs-built_in\">print<\/span>(word.text,  word.pos_)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Manchester PROPN\nUnited PROPN\nis VERB\nlooking VERB\nto PART\nsign VERB\na DET\nforward NOUN\nfor ADP\n$ SYM\n90 NUM\nmillion NUM\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0628\u0647 \u0647\u0631 \u06a9\u0644\u0645\u0647 \u06cc\u0627 \u0646\u0634\u0627\u0646\u0647 \u062f\u0631 \u062c\u0645\u0644\u0647 \u0645\u0627 \u0628\u062e\u0634\u06cc \u0627\u0632 \u06af\u0641\u062a\u0627\u0631 \u0627\u062e\u062a\u0635\u0627\u0635 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c &#8220;\u0645\u0646\u0686\u0633\u062a\u0631&#8221; \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0627\u0633\u0645 \u062e\u0627\u0635\u060c &#8220;\u0646\u06af\u0627\u0647 \u06a9\u0631\u062f\u0646&#8221; \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0641\u0639\u0644 \u0628\u0631\u0686\u0633\u0628 \u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0627\u0633\u062a\u060c \u0648 \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062a\u0631\u062a\u06cc\u0628 \u0631\u0648\u06cc.<\/p>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0628\u062e\u0634 \u0647\u0627\u06cc \u06af\u0641\u062a\u0627\u0631\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0648\u0627\u0628\u0633\u062a\u06af\u06cc \u0647\u0627 \u0631\u0627 \u0646\u06cc\u0632 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0633\u0646\u062f \u062f\u06cc\u06af\u0631 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">sentence2 = sp(<span class=\"hljs-string\">u\"Manchester United isn't looking to sign any forward.\"<\/span>)\n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 \u0648\u0627\u0628\u0633\u062a\u06af\u06cc\u060c \u0648\u06cc\u0698\u06af\u06cc <code>dep_<\/code> \u0645\u0637\u0627\u0628\u0642 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence2:\n    <span class=\"hljs-built_in\">print<\/span>(word.text,  word.pos_, word.dep_)\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\">Manchester PROPN compound\nUnited PROPN nsubj\nis VERB aux\nn't ADV neg\nlooking VERB ROOT\nto PART aux\nsign VERB xcomp\nany DET advmod\nforward ADV advmod\n. PUNCT punct\n<\/code><\/pre>\n<p>\u0627\u0632 \u062e\u0631\u0648\u062c\u06cc\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 spaCy \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u06a9\u0627\u0641\u06cc \u0647\u0648\u0634\u0645\u0646\u062f \u0627\u0633\u062a \u062a\u0627 \u0648\u0627\u0628\u0633\u062a\u06af\u06cc \u0628\u06cc\u0646 \u062a\u0648\u06a9\u0646 \u0647\u0627 \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u062f\u060c \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644 \u062f\u0631 \u062c\u0645\u0644\u0647 \u0645\u0627 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u062f\u0627\u0634\u062a\u06cc\u0645. <code>is'nt<\/code>.  \u062a\u062c\u0632\u06cc\u0647 \u06a9\u0646\u0646\u062f\u0647 \u0648\u0627\u0628\u0633\u062a\u06af\u06cc \u0622\u0646 \u0631\u0627 \u0628\u0647 \u062f\u0648 \u06a9\u0644\u0645\u0647 \u062a\u0642\u0633\u06cc\u0645 \u06a9\u0631\u062f\u0647 \u0648 \u0645\u0634\u062e\u0635 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 <code>n't<\/code> \u062f\u0631 \u0648\u0627\u0642\u0639 \u0646\u0641\u06cc \u06a9\u0644\u0645\u0647 \u0642\u0628\u0644\u06cc \u0627\u0633\u062a.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u062f\u0631\u06a9 \u062f\u0642\u06cc\u0642 \u062a\u062c\u0632\u06cc\u0647 \u0648\u0627\u0628\u0633\u062a\u06af\u06cc\u060c \u0645\u0631\u0627\u062c\u0639\u0647 \u06a9\u0646\u06cc\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/nlp.stanford.edu\/software\/dependencies_manual.pdf\">\u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647<\/a>.<\/p>\n<p>\u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0686\u0627\u067e \u06a9\u0644\u0645\u0627\u062a\u060c \u0634\u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f print \u062c\u0645\u0644\u0627\u062a \u0627\u0632 \u06cc\u06a9 \u0633\u0646\u062f<\/p>\n<pre><code class=\"hljs\">document = sp(<span class=\"hljs-string\">u'Hello from rasanegar. The site with the best Python Tutorials. What are you looking for?'<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0647\u0631 \u062c\u0645\u0644\u0647 \u0631\u0627 \u062a\u06a9\u0631\u0627\u0631 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> sentence <span class=\"hljs-keyword\">in<\/span> document.sents:\n    <span class=\"hljs-built_in\">print<\/span>(sentence)\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Hello from rasanegar.\nThe site with the best Python Tutorials.\nWhat are you looking for?\n<\/code><\/pre>\n<p>\u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0631\u0631\u0633\u06cc \u06a9\u0646\u06cc\u062f \u06a9\u0647 \u0622\u06cc\u0627 \u06cc\u06a9 \u062c\u0645\u0644\u0647 \u0628\u0627 \u06cc\u06a9 \u0646\u0634\u0627\u0646\u0647 \u062e\u0627\u0635 \u0634\u0631\u0648\u0639 \u0645\u06cc \u0634\u0648\u062f \u06cc\u0627 \u062e\u06cc\u0631.  \u0634\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u062a\u0648\u06a9\u0646 \u0647\u0627\u06cc \u062c\u062f\u0627\u06af\u0627\u0646\u0647 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0634\u0627\u062e\u0635 \u0648 \u0628\u0631\u0627\u06a9\u062a \u0647\u0627\u06cc \u0645\u0631\u0628\u0639\u06cc \u0645\u0627\u0646\u0646\u062f \u06cc\u06a9 \u0622\u0631\u0627\u06cc\u0647 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">document(<span class=\"hljs-number\">4<\/span>)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0645\u0627 \u0628\u0647 \u062f\u0646\u0628\u0627\u0644 \u06a9\u0644\u0645\u0647 5 \u062f\u0631 \u0633\u0646\u062f \u0647\u0633\u062a\u06cc\u0645.  \u0628\u0647 \u062e\u0627\u0637\u0631 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u06a9\u0647 \u0634\u0627\u062e\u0635 \u0627\u0632 \u0635\u0641\u0631 \u0634\u0631\u0648\u0639 \u0645\u06cc \u0634\u0648\u062f \u0648 \u062f\u0648\u0631\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0646\u0634\u0627\u0646\u0647 \u0628\u0647 \u062d\u0633\u0627\u0628 \u0645\u06cc \u0622\u06cc\u062f.  \u062f\u0631 \u062e\u0631\u0648\u062c\u06cc \u0628\u0627\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">The\n<\/code><\/pre>\n<p>\u062d\u0627\u0644\u0627 \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0622\u06cc\u0627 \u062c\u0645\u0644\u0647 \u0627\u06cc \u062f\u0631 \u0633\u0646\u062f \u0628\u0627 \u0622\u0646 \u0634\u0631\u0648\u0639 \u0645\u06cc \u0634\u0648\u062f \u06cc\u0627 \u062e\u06cc\u0631 <code>The<\/code>\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645 <code>is_sent_start<\/code> \u0648\u06cc\u0698\u06af\u06cc \u0645\u0637\u0627\u0628\u0642 \u0634\u06a9\u0644 \u0632\u06cc\u0631:<\/p>\n<pre><code class=\"hljs\">document(<span class=\"hljs-number\">4<\/span>).is_sent_start\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc\u060c \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f <code>True<\/code> \u0627\u0632 \u0632\u0645\u0627\u0646 \u0646\u0634\u0627\u0646\u0647 <code>The<\/code> \u062f\u0631 \u0627\u0628\u062a\u062f\u0627\u06cc \u062c\u0645\u0644\u0647 \u062f\u0648\u0645 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0628\u062e\u0634\u060c \u0686\u0646\u062f \u0639\u0645\u0644\u06cc\u0627\u062a \u0627\u0633\u0627\u0633\u06cc \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 spaCy \u0631\u0627 \u062f\u06cc\u062f\u06cc\u0645.  \u0627\u06a9\u0646\u0648\u0646 \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0639\u0645\u06cc\u0642\u200c\u062a\u0631 \u06a9\u0627\u0648\u0634 \u06a9\u0646\u06cc\u0645 \u0648 Tokenization\u060c Stemming \u0648 Lemmatization \u0631\u0627 \u0628\u0627 \u062c\u0632\u0626\u06cc\u0627\u062a \u0628\u0628\u06cc\u0646\u06cc\u0645.<\/p>\n<h2 id=\"tokenization\"><span class=\"ez-toc-section\" id=\"%d8%aa%d9%88%da%a9%d9%86_%d8%b3%d8%a7%d8%b2%db%8c\"><\/span>\u062a\u0648\u06a9\u0646 \u0633\u0627\u0632\u06cc<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0642\u0628\u0644\u0627\u064b \u062a\u0648\u0636\u06cc\u062d \u062f\u0627\u062f\u0647 \u0634\u062f\u060c \u062a\u0648\u06a9\u0646 \u0633\u0627\u0632\u06cc \u0647\u0645\u0627\u0646 \u0627\u0633\u062a process \u062a\u062c\u0632\u06cc\u0647 \u06cc\u06a9 \u0633\u0646\u062f \u0628\u0647 \u06a9\u0644\u0645\u0627\u062a\u060c \u0639\u0644\u0627\u0626\u0645 \u0646\u06af\u0627\u0631\u0634\u06cc\u060c \u0627\u0631\u0642\u0627\u0645 \u0639\u062f\u062f\u06cc \u0648 \u063a\u06cc\u0631\u0647.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u062a\u0648\u06a9\u0646\u06cc\u0632\u0627\u0633\u06cc\u0648\u0646 spaCy \u0631\u0627 \u0628\u0627 \u062c\u0632\u0626\u06cc\u0627\u062a \u0628\u0628\u06cc\u0646\u06cc\u0645.  \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u06cc\u06a9 \u0633\u0646\u062f \u062c\u062f\u06cc\u062f \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">sentence3 = sp(<span class=\"hljs-string\">u'\"They\\'re leaving U.K. for U.S.A.\"'<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(sentence3)\n<\/code><\/pre>\n<p>\u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u062c\u0645\u0644\u0647 \u0634\u0627\u0645\u0644 \u0646\u0642\u0644 \u0642\u0648\u0644 \u062f\u0631 \u0627\u0628\u062a\u062f\u0627 \u0648 \u062f\u0631 \u067e\u0627\u06cc\u0627\u0646 \u0627\u0633\u062a.  \u0647\u0645\u0686\u0646\u06cc\u0646 \u062f\u0627\u0631\u0627\u06cc \u0639\u0644\u0627\u0626\u0645 \u0646\u06af\u0627\u0631\u0634\u06cc \u0628\u0647 \u0635\u0648\u0631\u062a \u0627\u062e\u062a\u0635\u0627\u0631\u06cc &#8220;UK&#8221; \u0648 &#8220;USA&#8221; \u0627\u0633\u062a.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u06a9\u0647 spaCy \u0686\u06af\u0648\u0646\u0647 \u0627\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0631\u0627 \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence3:\n    <span class=\"hljs-built_in\">print<\/span>(word.text)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">\"\nThey\n're\nleaving\nU.K.\nfor\nU.S.A.\n\"\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc\u060c \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 spaCy \u062f\u0648 \u0646\u0642\u0644 \u0642\u0648\u0644 \u0634\u0631\u0648\u0639 \u0648 \u067e\u0627\u06cc\u0627\u0646 \u0631\u0627 \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u06a9\u0631\u062f\u0647 \u0627\u0633\u062a.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u06a9\u0627\u0641\u06cc \u0647\u0648\u0634\u0645\u0646\u062f \u0627\u0633\u062a\u060c \u0646\u0647 \u0627\u06cc\u0646\u06a9\u0647 \u0646\u0642\u0637\u0647 \u0646\u06af\u0627\u0631\u0634\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0634\u062f\u0647 \u0628\u06cc\u0646 \u0627\u062e\u062a\u0635\u0627\u0631\u0627\u062a\u06cc \u0645\u0627\u0646\u0646\u062f UK \u0648 USA \u0631\u0627 \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0646\u0645\u0648\u0646\u0647 \u062f\u06cc\u06af\u0631\u06cc \u0627\u0632 \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">sentence4 = sp(<span class=\"hljs-string\">u\"Hello, I am non-vegetarian, email me the menu at (email\u00a0protected)\"<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(sentence4)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u062f\u0631 \u062c\u0645\u0644\u0647 \u0628\u0627\u0644\u0627 \u06cc\u06a9 \u062e\u0637 \u062a\u06cc\u0631\u0647 \u062f\u0631 \u06a9\u0644\u0645\u0647 &#8220;\u063a\u06cc\u0631 \u06af\u06cc\u0627\u0647\u062e\u0648\u0627\u0631\u06cc&#8221; \u0648 \u062f\u0631 \u0622\u062f\u0631\u0633 \u0627\u06cc\u0645\u06cc\u0644 \u062f\u0627\u0631\u06cc\u0645.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u06a9\u0647 spaCy \u0686\u06af\u0648\u0646\u0647 \u0627\u06cc\u0646 \u0631\u0627 \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence4:\n    <span class=\"hljs-built_in\">print<\/span>(word.text)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Hello\n,\nI\nam\nnon\n-\nvegetarian\n,\nemail\nme\nthe\nmenu\nat\n(email\u00a0protected)\n<\/code><\/pre>\n<p>\u0627\u0632 \u062e\u0631\u0648\u062c\u06cc \u0645\u0634\u062e\u0635 \u0627\u0633\u062a \u06a9\u0647 spaCy \u062f\u0631 \u0648\u0627\u0642\u0639 \u0642\u0627\u062f\u0631 \u0628\u0647 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0627\u06cc\u0645\u06cc\u0644 \u0628\u0648\u062f\u0647 \u0648 \u0639\u0644\u06cc\u0631\u063a\u0645 \u062f\u0627\u0634\u062a\u0646 &#8220;-&#8220;\u060c \u0622\u0646 \u0631\u0627 \u062a\u0648\u06a9\u0646 \u0646\u06a9\u0631\u062f\u0647 \u0627\u0633\u062a.  \u0627\u0632 \u0637\u0631\u0641\u06cc \u06a9\u0644\u0645\u0647 \u00ab\u063a\u06cc\u0631 \u06af\u06cc\u0627\u0647\u062e\u0648\u0627\u0631\u06cc\u00bb \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u0634\u062f.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0633\u0646\u062f \u0631\u0627 \u0628\u0634\u0645\u0627\u0631\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-built_in\">len<\/span>(sentence4)\n<\/code><\/pre>\n<p>\u062f\u0631 \u062e\u0631\u0648\u062c\u06cc\u060c 14 \u0639\u062f\u062f \u0631\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u062e\u0648\u0627\u0647\u06cc\u062f \u06a9\u0631\u062f \u06a9\u0647 \u062a\u0639\u062f\u0627\u062f \u062a\u0648\u06a9\u0646 \u0647\u0627\u06cc \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0622\u0646 \u0627\u0633\u062a <code>sentence4<\/code>.<\/p>\n<h3 id=\"detectingentities\"><span class=\"ez-toc-section\" id=\"%d8%b4%d9%86%d8%a7%d8%b3%d8%a7%db%8c%db%8c_%d9%85%d9%88%d8%ac%d9%88%d8%af%db%8c%d8%aa_%d9%87%d8%a7\"><\/span>\u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0647\u0627<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u062a\u0648\u06a9\u0646 \u06a9\u0631\u062f\u0646 \u0627\u0633\u0646\u0627\u062f \u0628\u0647 \u06a9\u0644\u0645\u0627\u062a\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0645\u062a\u0648\u062c\u0647 \u0634\u0648\u06cc\u062f \u06a9\u0647 \u0622\u06cc\u0627 \u06a9\u0644\u0645\u0647 \u0645\u0648\u062c\u0648\u062f\u06cc \u0627\u0633\u062a \u0645\u0627\u0646\u0646\u062f \u0634\u0631\u06a9\u062a\u060c \u0645\u06a9\u0627\u0646\u060c \u0633\u0627\u062e\u062a\u0645\u0627\u0646\u060c \u0627\u0631\u0632\u060c \u0645\u0648\u0633\u0633\u0647 \u0648 \u063a\u06cc\u0631\u0647.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0645\u062b\u0627\u0644 \u0633\u0627\u062f\u0647 \u0627\u0632 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">sentence5 = sp(<span class=\"hljs-string\">u'Manchester United is looking to sign Harry Kane for $90 million'<\/span>)  \n<\/code><\/pre>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u0628\u062a\u062f\u0627 \u0633\u0639\u06cc \u06a9\u0646\u06cc\u0645 \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u0622\u0646 \u0631\u0627 \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence5:\n    <span class=\"hljs-built_in\">print<\/span>(word.text)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Manchester\nUnited\nis\nlooking\nto\nsign\nHarry\nKane\nfor\n$\n90\nmillion\n<\/code><\/pre>\n<p>\u0645\u0627 \u0645\u06cc \u062f\u0627\u0646\u06cc\u0645 \u06a9\u0647 &#8220;\u0645\u0646\u0686\u0633\u062a\u0631\u06cc\u0648\u0646\u0627\u06cc\u062a\u062f&#8221; \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u0627\u0633\u062a\u060c \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u0646\u0628\u0627\u06cc\u062f \u0622\u0646 \u0631\u0627 \u0628\u0647 \u062f\u0648 \u06a9\u0644\u0645\u0647 \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0631\u062f.  \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062a\u0631\u062a\u06cc\u0628\u060c &#8220;\u0647\u0631\u06cc \u06a9\u06cc\u0646&#8221; \u0646\u0627\u0645 \u06cc\u06a9 \u0634\u062e\u0635 \u0627\u0633\u062a \u0648 &#8220;90 \u0645\u06cc\u0644\u06cc\u0648\u0646 \u062f\u0644\u0627\u0631&#8221; \u06cc\u06a9 \u0627\u0631\u0632\u0634 \u0627\u0631\u0632\u06cc \u0627\u0633\u062a.  \u0627\u06cc\u0646\u0647\u0627 \u0647\u0645 \u0646\u0628\u0627\u06cc\u062f \u062a\u0648\u06a9\u0646\u06cc\u0632\u0647 \u0634\u0648\u0646\u062f.<\/p>\n<p>\u0627\u06cc\u0646\u062c\u0627\u0633\u062a \u06a9\u0647 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Named-entity_recognition\">\u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647<\/a> \u0628\u0631\u0627\u06cc \u0628\u0627\u0632\u06cc \u0645\u06cc \u0622\u06cc\u062f  \u0628\u0631\u0627\u06cc \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0647\u0627\u06cc \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0633\u0646\u062f\u060c \u0628\u0627\u06cc\u062f \u0627\u0632 \u0622\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u062f <code>ents<\/code> \u0635\u0641\u062a.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0647\u0627\u06cc \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0631\u0627 \u0627\u0632 \u062c\u0645\u0644\u0647 \u0628\u0627\u0644\u0627 \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u06a9\u0646\u06cc\u0645.  \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> entity <span class=\"hljs-keyword\">in<\/span> sentence.ents:\n    <span class=\"hljs-built_in\">print<\/span>(entity.text + <span class=\"hljs-string\">' - '<\/span> + entity.label_ + <span class=\"hljs-string\">' - '<\/span> + <span class=\"hljs-built_in\">str<\/span>(spacy.explain(entity.label_)))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0645\u0627 print \u0645\u062a\u0646 \u0645\u0648\u062c\u0648\u062f\u06cc\u062a\u060c \u0628\u0631\u0686\u0633\u0628 \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0648 \u062c\u0632\u0626\u06cc\u0627\u062a \u0645\u0648\u062c\u0648\u062f\u06cc\u062a.  \u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Manchester United - ORG - Companies, agencies, institutions, etc.\nHarry Kane - PERSON - People, including fictional\n$90 million - MONEY - Monetary values, including unit\n<\/code><\/pre>\n<p>\u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0633\u0627\u0632\u0645\u0627\u0646 \u0641\u0636\u0627\u06cc\u06cc SpaCy \u0628\u0627 \u0645\u0648\u0641\u0642\u06cc\u062a \u00ab\u0645\u0646\u0686\u0633\u062a\u0631 \u06cc\u0648\u0646\u0627\u06cc\u062a\u062f\u00bb \u0631\u0627 \u0628\u0647\u200c\u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0633\u0627\u0632\u0645\u0627\u0646\u060c \u00ab\u0647\u0631\u06cc \u06a9\u06cc\u0646\u00bb \u0631\u0627 \u0628\u0647\u200c\u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0634\u062e\u0635 \u0648 \u00ab\u06f9\u06f0 \u0645\u06cc\u0644\u06cc\u0648\u0646 \u062f\u0644\u0627\u0631\u00bb \u0631\u0627 \u0628\u0647\u200c\u0639\u0646\u0648\u0627\u0646 \u0627\u0631\u0632\u0634 \u0627\u0631\u0632 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u06a9\u0631\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<h3 id=\"detectingnouns\"><span class=\"ez-toc-section\" id=\"%d8%aa%d8%b4%d8%ae%db%8c%d8%b5_%d8%a7%d8%b3%d9%85_%d9%87%d8%a7\"><\/span>\u062a\u0634\u062e\u06cc\u0635 \u0627\u0633\u0645 \u0647\u0627<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0647\u0627\u06cc \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647\u060c \u0627\u0633\u0627\u0645\u06cc \u0646\u06cc\u0632 \u0642\u0627\u0628\u0644 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0647\u0633\u062a\u0646\u062f.  \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u06cc\u0646 \u06a9\u0627\u0631\u060c <code>noun_chunks<\/code> \u0648\u06cc\u0698\u06af\u06cc \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u062c\u0645\u0644\u0647 \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u0646\u0638\u0631 \u0628\u06af\u06cc\u0631\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">sentence5 = sp(<span class=\"hljs-string\">u'Latest Rumours: Manchester United is looking to sign Harry Kane for $90 million'<\/span>)  \n<\/code><\/pre>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0633\u0639\u06cc \u06a9\u0646\u06cc\u0645 \u0627\u0633\u0645 \u0647\u0627\u06cc \u0627\u06cc\u0646 \u062c\u0645\u0644\u0647 \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> noun <span class=\"hljs-keyword\">in<\/span> sentence5.noun_chunks:\n    <span class=\"hljs-built_in\">print<\/span>(noun.text)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Latest Rumours\nManchester United\nHarry Kane\n<\/code><\/pre>\n<p>\u0627\u0632 \u062e\u0631\u0648\u062c\u06cc\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u06cc\u06a9 \u0627\u0633\u0645 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u06cc\u06a9 \u0645\u0648\u062c\u0648\u062f\u06cc\u062a \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0646\u06cc\u0632 \u0628\u0627\u0634\u062f \u0648 \u0628\u0627\u0644\u0639\u06a9\u0633.<\/p>\n<h2 id=\"stemming\"><span class=\"ez-toc-section\" id=\"%d8%b3%d8%a7%d9%82%d9%87\"><\/span>\u0633\u0627\u0642\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Stemming \u0628\u0647 \u06a9\u0627\u0647\u0634 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u0628\u0647 \u0622\u0646 \u0627\u0634\u0627\u0631\u0647 \u062f\u0627\u0631\u062f root \u0641\u0631\u0645.  \u062f\u0631 \u062d\u06cc\u0646 \u0627\u0646\u062c\u0627\u0645 \u0648\u0638\u0627\u06cc\u0641 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc\u060c \u0628\u0627 \u0633\u0646\u0627\u0631\u06cc\u0648\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641\u06cc \u0631\u0648\u0628\u0631\u0648 \u0645\u06cc \u0634\u0648\u06cc\u062f \u06a9\u0647 \u062f\u0631 \u0622\u0646 \u06a9\u0644\u0645\u0627\u062a \u0645\u062e\u062a\u0644\u0641\u06cc \u0628\u0627 \u06cc\u06a9\u0633\u0627\u0646 \u067e\u06cc\u062f\u0627 \u0645\u06cc \u06a9\u0646\u06cc\u062f. root.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u0645\u062d\u0627\u0633\u0628\u0647\u060c \u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631\u060c \u0645\u062d\u0627\u0633\u0628\u0627\u062a\u060c \u0645\u062d\u0627\u0633\u0628\u0647 \u0648 \u063a\u06cc\u0631\u0647. \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0628\u062e\u0648\u0627\u0647\u06cc\u062f \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0647 \u0622\u0646\u0647\u0627 \u06a9\u0627\u0647\u0634 \u062f\u0647\u06cc\u062f. root \u0641\u0631\u0645 \u0628\u0647 \u062e\u0627\u0637\u0631 \u06cc\u06a9\u0646\u0648\u0627\u062e\u062a\u06cc  \u0627\u06cc\u0646\u062c\u0627\u0633\u062a \u06a9\u0647 stemming \u0648\u0627\u0631\u062f \u0639\u0645\u0644 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0628\u0631\u0627\u06cc \u0634\u0645\u0627 \u062a\u0639\u062c\u0628 \u0622\u0648\u0631 \u0628\u0627\u0634\u062f\u060c \u0627\u0645\u0627 spaCy \u0622\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0645\u062a\u06a9\u06cc \u0627\u0633\u062a \u062f\u0627\u0631\u0627\u06cc \u0647\u06cc\u0686 \u0639\u0645\u0644\u06a9\u0631\u062f\u06cc \u0628\u0631\u0627\u06cc stemming \u0646\u06cc\u0633\u062a \u0631\u0648\u06cc \u0641\u0642\u0637 \u0648\u0627\u0698\u0647 \u0633\u0627\u0632\u06cc  \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u062f\u0631 \u0627\u06cc\u0646 \u0642\u0633\u0645\u062a \u0627\u0632 NLTK \u0628\u0631\u0627\u06cc stemming \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645.<\/p>\n<p>\u062f\u0648 \u0646\u0648\u0639 \u0633\u0627\u0642\u0647 \u062f\u0631 NLTK \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f: <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/tartarus.org\/martin\/PorterStemmer\/\">\u067e\u0648\u0631\u062a\u0631 \u0627\u0633\u062a\u0645\u0631<\/a> \u0648 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/tartarus.org\/martin\/PorterStemmer\/\">\u0633\u0627\u0642\u0647 \u0647\u0627\u06cc \u06af\u0644\u0648\u0644\u0647 \u0628\u0631\u0641\u06cc<\/a>.  \u0647\u0631 \u062f\u0648\u06cc \u0622\u0646\u0647\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0634\u062f\u0647 \u0627\u0646\u062f.<\/p>\n<h3 id=\"porterstemmer\"><span class=\"ez-toc-section\" id=\"%d9%be%d9%88%d8%b1%d8%aa%d8%b1_%d8%a7%d8%b3%d8%aa%d9%85%d8%b1\"><\/span>\u067e\u0648\u0631\u062a\u0631 \u0627\u0633\u062a\u0645\u0631<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u067e\u0648\u0631\u062a\u0631 \u0627\u0633\u062a\u0645\u0631 \u0631\u0627 \u062f\u0631 \u0639\u0645\u0644 \u0628\u0628\u06cc\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> nltk\n\n<span class=\"hljs-keyword\">from<\/span> nltk.stem.porter <span class=\"hljs-keyword\">import<\/span> *\n<\/code><\/pre>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u06a9\u0644\u0627\u0633 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645 <code>PorterStemmer<\/code>.<\/p>\n<pre><code class=\"hljs\">stemmer = PorterStemmer()\n<\/code><\/pre>\n<p>\u0641\u0631\u0636 \u06a9\u0646\u06cc\u062f \u0645\u0627 \u0644\u06cc\u0633\u062a \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0627\u0631\u06cc\u0645 \u0648 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645 \u0627\u06cc\u0646 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0647 \u0631\u06cc\u0634\u0647 \u06a9\u0627\u0647\u0634 \u062f\u0647\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">tokens = (<span class=\"hljs-string\">'compute'<\/span>, <span class=\"hljs-string\">'computer'<\/span>, <span class=\"hljs-string\">'computed'<\/span>, <span class=\"hljs-string\">'computing'<\/span>)\n<\/code><\/pre>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 porter stemmer \u0631\u06cc\u0634\u0647 \u06a9\u0644\u0645\u0627\u062a \u0645\u0648\u062c\u0648\u062f \u062f\u0631 \u0644\u06cc\u0633\u062a \u0631\u0627 \u067e\u06cc\u062f\u0627 \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> token <span class=\"hljs-keyword\">in<\/span> tokens:\n    <span class=\"hljs-built_in\">print<\/span>(token + <span class=\"hljs-string\">' --&gt; '<\/span> + stemmer.stem(token))\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">compute --&gt; comput\ncomputer --&gt; comput\ncomputed --&gt; comput\ncomputing --&gt; comput\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u062a\u0645\u0627\u0645 4 \u06a9\u0644\u0645\u0647 \u0628\u0647 &#8220;comput&#8221; \u06a9\u0627\u0647\u0634 \u06cc\u0627\u0641\u062a\u0647 \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0648\u0627\u0642\u0639 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u0646\u06cc\u0633\u062a.<\/p>\n<h3 id=\"snowballstemmer\"><span class=\"ez-toc-section\" id=\"%d8%a7%d8%b3%d8%aa%d9%85%d8%b1_%da%af%d9%84%d9%88%d9%84%d9%87_%d8%a8%d8%b1%d9%81%db%8c\"><\/span>\u0627\u0633\u062a\u0645\u0631 \u06af\u0644\u0648\u0644\u0647 \u0628\u0631\u0641\u06cc<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0633\u0627\u0642\u0647 \u06af\u0644\u0648\u0644\u0647 \u0628\u0631\u0641\u06cc \u06cc\u06a9 \u0646\u0633\u062e\u0647 \u06a9\u0645\u06cc \u0628\u0647\u0628\u0648\u062f \u06cc\u0627\u0641\u062a\u0647 \u0627\u0632 \u0633\u0627\u0642\u0647 \u067e\u0648\u0631\u062a\u0631 \u0627\u0633\u062a \u0648 \u0645\u0639\u0645\u0648\u0644\u0627 \u0628\u0631 \u062f\u0648\u0645\u06cc \u062a\u0631\u062c\u06cc\u062d \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0633\u0627\u0642\u0647 \u06af\u0644\u0648\u0644\u0647 \u0628\u0631\u0641\u06cc \u0631\u0627 \u062f\u0631 \u0639\u0645\u0644 \u0628\u0628\u06cc\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> nltk.stem.snowball <span class=\"hljs-keyword\">import<\/span> SnowballStemmer\n\nstemmer = SnowballStemmer(language=<span class=\"hljs-string\">'english'<\/span>)\n\ntokens = (<span class=\"hljs-string\">'compute'<\/span>, <span class=\"hljs-string\">'computer'<\/span>, <span class=\"hljs-string\">'computed'<\/span>, <span class=\"hljs-string\">'computing'<\/span>)\n\n<span class=\"hljs-keyword\">for<\/span> token <span class=\"hljs-keyword\">in<\/span> tokens:\n    <span class=\"hljs-built_in\">print<\/span>(token + <span class=\"hljs-string\">' --&gt; '<\/span> + stemmer.stem(token))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u0645\u0627 \u0627\u0632 Snowball stemmer \u0628\u0631\u0627\u06cc \u06cc\u0627\u0641\u062a\u0646 \u0631\u06cc\u0634\u0647 \u0647\u0645\u0627\u0646 4 \u06a9\u0644\u0645\u0647 \u0627\u06cc \u06a9\u0647 \u0628\u0627 porter stemmer \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f\u06cc\u0645\u060c \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f\u06cc\u0645.  \u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">compute --&gt; comput\ncomputer --&gt; comput\ncomputed --&gt; comput\ncomputing --&gt; comput\n<\/code><\/pre>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0646\u062a\u0627\u06cc\u062c \u06cc\u06a9\u0633\u0627\u0646 \u0627\u0633\u062a.  \u0645\u0627 \u0647\u0646\u0648\u0632 &#8220;\u0645\u062d\u0627\u0633\u0628\u0647&#8221; \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u067e\u0627\u06cc\u0647 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0631\u062f\u06cc\u0645.  \u0628\u0627\u0632 \u0647\u0645\u060c \u0627\u06cc\u0646 \u06a9\u0644\u0645\u0647 &#8220;\u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631&#8221; \u062f\u0631 \u0648\u0627\u0642\u0639 \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0646\u06cc\u0633\u062a.<\/p>\n<p>\u0627\u06cc\u0646\u062c\u0627\u0633\u062a \u06a9\u0647 \u06a9\u0644\u0645\u0647 \u0646\u0648\u06cc\u0633\u06cc \u0645\u0641\u06cc\u062f \u0627\u0633\u062a.  Lemmatization \u06a9\u0644\u0645\u0647 \u0631\u0627 \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0622\u0645\u062f\u0647 \u0628\u0647 \u0631\u06cc\u0634\u0647 \u062e\u0648\u062f \u06a9\u0627\u0647\u0634 \u0645\u06cc \u062f\u0647\u062f.  \u0631\u06cc\u0634\u0647\u200c\u0647\u0627\u06cc\u06cc \u06a9\u0647 \u0627\u0632 \u0637\u0631\u06cc\u0642 \u0648\u0627\u0698\u0647\u200c\u0633\u0627\u0632\u06cc \u0628\u0631\u06af\u0631\u062f\u0627\u0646\u062f\u0647 \u0645\u06cc\u200c\u0634\u0648\u0646\u062f\u060c \u0648\u0627\u0698\u0647\u200c\u0647\u0627\u06cc \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0648\u0627\u0642\u0639\u06cc \u0647\u0633\u062a\u0646\u062f \u0648 \u0628\u0631\u062e\u0644\u0627\u0641 \u06a9\u0644\u0645\u0627\u062a\u06cc \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0627\u0633\u062a\u0645\u0631 \u0628\u0631\u06af\u0631\u062f\u0627\u0646\u062f\u0647 \u0645\u06cc\u200c\u0634\u0648\u0646\u062f\u060c \u0627\u0632 \u0646\u0638\u0631 \u0645\u0639\u0646\u0627\u06cc\u06cc \u06a9\u0627\u0645\u0644 \u0647\u0633\u062a\u0646\u062f.<\/p>\n<h3 id=\"lemmatization\"><span class=\"ez-toc-section\" id=\"lemmatization\"><\/span>Lemmatization<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0627\u06af\u0631\u0686\u0647 \u0645\u0627 \u0646\u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 stemming \u0631\u0627 \u0628\u0627 spaCy \u0627\u0646\u062c\u0627\u0645 \u062f\u0647\u06cc\u0645\u060c \u0627\u0645\u0627 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 spaCy \u0648\u0627\u0698\u0647\u200c\u0633\u0627\u0632\u06cc \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u062f\u0647\u06cc\u0645.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0628\u0627\u06cc\u062f \u0627\u0632 <code>lemma_<\/code> \u0635\u0641\u062a \u0631\u0648\u06cc \u0633\u0646\u062f spaCy  \u0641\u0631\u0636 \u06a9\u0646\u06cc\u062f \u062c\u0645\u0644\u0647 \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0627\u0631\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">sentence6 = sp(<span class=\"hljs-string\">u'compute computer computed computing'<\/span>)\n<\/code><\/pre>\n<p>\u0645\u0627 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0631\u06cc\u0634\u0647 \u0647\u0645\u0647 \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0648\u0627\u0698\u0647\u200c\u0633\u0627\u0632\u06cc spaCy \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence6:\n    <span class=\"hljs-built_in\">print<\/span>(word.text,  word.lemma_)\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u0628\u0647 \u0634\u06a9\u0644 \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">compute compute\ncomputer computer\ncomputed compute\ncomputing computing\n<\/code><\/pre>\n<p>\u0634\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0628\u0631 \u062e\u0644\u0627\u0641 stemming \u06a9\u0647 \u062f\u0631 \u0622\u0646 root \u0645\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0631\u062f\u06cc\u0645 &#8220;\u0645\u062d\u0627\u0633\u0628\u0647&#8221; \u0628\u0648\u062f\u060c \u0631\u06cc\u0634\u0647 \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0647 \u062f\u0633\u062a \u0622\u0648\u0631\u062f\u06cc\u0645 \u06a9\u0644\u0645\u0627\u062a \u0648\u0627\u0642\u0639\u06cc \u062f\u0631 \u0641\u0631\u0647\u0646\u06af \u0644\u063a\u062a \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>Lemmatization \u06a9\u0644\u0645\u0627\u062a \u0631\u0627 \u062f\u0631 \u0634\u06a9\u0644 \u062f\u0648\u0645 \u06cc\u0627 \u0633\u0648\u0645 \u0628\u0647 \u0627\u0646\u0648\u0627\u0639 \u0634\u06a9\u0644 \u0627\u0648\u0644 \u062e\u0648\u062f \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u0647 \u0645\u062b\u0627\u0644 \u0632\u06cc\u0631 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">sentence7 = sp(<span class=\"hljs-string\">u'A letter has been written, asking him to be released'<\/span>)\n\n<span class=\"hljs-keyword\">for<\/span> word <span class=\"hljs-keyword\">in<\/span> sentence7:\n    <span class=\"hljs-built_in\">print<\/span>(word.text + <span class=\"hljs-string\">'  ===&gt;'<\/span>, word.lemma_)\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">A ===&gt; a\nletter ===&gt; letter\nhas ===&gt; have\nbeen ===&gt; be\nwritten ===&gt; write\n, ===&gt; ,\nasking ===&gt; ask\nhim ===&gt; -PRON-\nto ===&gt; to\nbe ===&gt; be\nreleased ===&gt; release\n<\/code><\/pre>\n<p>\u0627\u0632 \u062e\u0631\u0648\u062c\u06cc \u0628\u0647 \u0648\u0636\u0648\u062d \u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u06a9\u0644\u0645\u0627\u062a \u062f\u0631 \u0641\u0631\u0645 \u0647\u0627\u06cc \u062f\u0648\u0645 \u0648 \u0633\u0648\u0645 \u0645\u0627\u0646\u0646\u062f &#8220;\u0646\u0648\u0634\u062a\u0647&#8221;\u060c &#8220;\u0622\u0632\u0627\u062f \u0634\u062f\u0647&#8221; \u0648 &#8230; \u0628\u0647 \u0634\u06a9\u0644 \u0627\u0648\u0644 \u06cc\u0639\u0646\u06cc &#8220;\u0646\u0648\u0634\u062a\u0646&#8221; \u0648 &#8220;\u0631\u0647\u0627 \u06a9\u0631\u062f\u0646&#8221; \u062a\u0628\u062f\u06cc\u0644 \u0634\u062f\u0647 \u0627\u0646\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>Tokenization\u060c Stemming \u0648 Lemmatization \u0628\u0631\u062e\u06cc \u0627\u0632 \u0627\u0633\u0627\u0633\u06cc \u062a\u0631\u06cc\u0646 \u0648\u0638\u0627\u06cc\u0641 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc \u0647\u0633\u062a\u0646\u062f.  \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u062f\u06cc\u062f\u06cc\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 Tokenization \u0648 Lemmatization \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 spaCy \u0627\u0646\u062c\u0627\u0645 \u062f\u0647\u06cc\u0645.  \u0645\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u062f\u06cc\u062f\u06cc\u0645 \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 NLTK \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0631\u0627\u06cc stemming \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0634\u0648\u062f.  \u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0628\u0639\u062f\u06cc \u0628\u062d\u062b \u062e\u0648\u062f \u0631\u0627 \u062f\u0631 \u0645\u0648\u0631\u062f \u0648\u0627\u0698\u06af\u0627\u0646 \u0648 \u062a\u0637\u0628\u06cc\u0642 \u0639\u0628\u0627\u0631\u062a \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0622\u063a\u0627\u0632 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f.<\/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 1403-01-24 06:17:03<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;16373&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 \u0628\u0631\u0627\u06cc NLP: Tokenization\u060c Stemming \u0648 Lemmatization \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 SpaCy&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\"> 8<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span>\u062f\u0631 \u0645\u0642\u0627\u0644\u0647 \u0642\u0628\u0644\u06cc \u0628\u062d\u062b \u062e\u0648\u062f \u0631\u0627 \u062f\u0631 \u0645\u0648\u0631\u062f \u0631\u0648\u0634 \u0627\u0646\u062c\u0627\u0645 \u067e\u0631\u062f\u0627\u0632\u0634 \u0632\u0628\u0627\u0646 \u0637\u0628\u06cc\u0639\u06cc \u0628\u0627 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0634\u0631\u0648\u0639 \u06a9\u0631\u062f\u06cc\u0645. \u0631\u0648\u0634 \u062e\u0648\u0627\u0646\u062f\u0646 \u0648 \u0646\u0648\u0634\u062a\u0646 \u0641\u0627\u06cc\u0644 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0648 PDF \u0631\u0627 \u062f\u06cc\u062f\u06cc\u0645. \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647\u060c \u0645\u0627 \u0634\u0631\u0648\u0639 \u0628\u0647 \u06a9\u0627\u0631 \u0628\u0627 \u0641\u0636\u0627\u06cc\u06cc \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0686\u0646\u062f \u06a9\u0627\u0631 \u0627\u0633\u0627\u0633\u06cc NLP \u0645\u0627\u0646\u0646\u062f \u0646\u0634\u0627\u0646\u0647 \u06af\u0630\u0627\u0631\u06cc\u060c \u0631\u06cc\u0634\u0647 \u06cc\u0627\u0628\u06cc \u0648 \u0631\u06cc\u0634\u0647 \u06cc\u0627\u0628\u06cc. \u0645\u0639\u0631\u0641\u06cc SpaCy \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":9162,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1743,620],"tags":[],"class_list":["post-16373","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\/16373","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=16373"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16373\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media\/9162"}],"wp:attachment":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media?parent=16373"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=16373"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=16373"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}