fix typo

nlp_course.html

@@ -193,7 +193,7 @@ <h3>This new format of the course is designed for:</h3>
 
             <a href="#whats_inside_lectures">
                 Seminars & Homeworks
-                <br><span class="demo_sidebar_comment">notebooks in our 7k-☆ course repo</span>
+                <br><span class="demo_sidebar_comment">notebooks in our 7.3k-☆ course repo</span>
             </a>
             </div>
 
@@ -256,7 +256,7 @@ <h3 style="margin-bottom:2px;">Bonus:</h3>
 
             <h2 style="margin-bottom:2px;">Seminars & Homeworks</h2>
             <p class="data_text">For each topic, you can take notebooks from
-                <a href="https://github.com/yandexdataschool/nlp_course" target="_blank">our 7k-☆ course repo</a>.
+                <a href="https://github.com/yandexdataschool/nlp_course" target="_blank">our 7.3k-☆ course repo</a>.
             </p>
                <p class="data_text" style="margin-top:-7px;"> From 2020, both PyTorch and Tensorflow!
             </p>

nlp_course/text_classification.html

@@ -2300,7 +2300,7 @@ <h3><u><font face="arial" color="#79a123">P(x|y=k)</font>: use the "naive" assum
 
     <p>Here we assume that document \(x\) is represented as a set of features, e.g., a set
     of its words \((x_1, \dots, x_n)\):
-    \[P(x| y=k)=P(x_1, \dots, x_n|y).\]
+    \[P(x| y=k)=P(x_1, \dots, x_n|y=k).\]
     </p>
 
     <p><font face="arial">The Naive Bayes assumptions</font> are</p>
@@ -2324,7 +2324,7 @@ <h3><u><font face="arial" color="#79a123">P(x|y=k)</font>: use the "naive" assum
     </p>
 
     <p>With these <font face="arial">"naive"</font> assumptions we get:
-    \[P(x| y=k)=P(x_1, \dots, x_n|y)=\prod\limits_{t=1}^nP(x_t|y=k).\]
+    \[P(x| y=k)=P(x_1, \dots, x_n|y=k)=\prod\limits_{t=1}^nP(x_t|y=k).\]
 
         The probabilities \(P(x_i|y=k)\) are estimated as the proportion of times the word \(x_i\)
         appeared in documents of class \(k\) among all tokens in these documents: