Fix typos

lessons/5-NLP/19-NER/README.md

@@ -8,9 +8,9 @@ Up to now, we have mostly been concentrating on one NLP task - classification. H
 
 Suppose you want to develop a natural language chat bot, similar to Amazon Alexa or Google Assistant. The way intelligent chat bots work is to *understand* what the user want by doing text classification on the input sentence. The result of this classification is so-called **intent**, which determines what a chat bot should do.
 
-![Bot NER](images/bot-ner.png)
+<img alt="Bot NER" src="images/bot-ner.png" width="50%"/>
 
-> Image by author
+> *Image by author*
 
 However, a user may provide some parameters as part of the phrase. For example, when asking for a weather, she may specify a location or date. A bot should be able to understand those entities, and fill in the parameter slots accordingly before performing the action. This is exactly when NER comes in. 
 

lessons/X-Extras/X1-MultiModal/README.md

@@ -50,7 +50,7 @@ To generate an image corresponding to a text prompt, we start with some random e
 
 A great library that implements VQGAN+CLIP is [Pixray](http://github.com/pixray/pixray)
 
-![Picture produced by Pixray](images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png) |  ![Picture produced by pixray](images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png) | ![Picture produced by Pixray](a_closeup_oil_portrait_of_old_male_teacher_of_mathematics_in_front_of_blackboard.png)
+![Picture produced by Pixray](images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png) |  ![Picture produced by pixray](images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png) | ![Picture produced by Pixray](a_closeup_oil_portrait_of_old_male_teacher_of_math.png)
 ----|----|----
 Picture generated from prompt *a closeup watercolor portrait of young male teacher of literature with a book* | Picture generated from prompt *a closeup oil portrait of young female teacher of computer science with a computer* | Picture generated from prompt *a closeup oil portrait of old male teacher of mathematics in front of blackboard*
 
@@ -59,4 +59,4 @@ Picture generated from prompt *a closeup watercolor portrait of young male teach
 ## References
 
 * VQGAN Paper: [Taming Transformers for High-Resolution Image Synthesis](https://compvis.github.io/taming-transformers/paper/paper.pdf)
-* CLIP Paper: [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/pdf/2103.00020.pdf) 
+* CLIP Paper: [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/pdf/2103.00020.pdf)