edits for nlp

README.md

@@ -94,7 +94,7 @@ For a gentle introduction to *AI in the Cloud* topics you may consider taking th
 
 **[Mindmap of the Course](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
 
-Each lesson contains some pre-reading material (linked as **Text** above), and some executable Jupyter Notebooks, which are often specific to the framework (**PyTorch** or **TensorFlow**). The executable notebook also contains a lot of theoretical material, so to understand the topic you need to go through at least one version of the notebooks (either PyTorch or TensorFlow). There are also **Labs** available for some topics, which give you an opportunity to try applying the material you have learnt to a specific problem. 
+Each lesson contains some pre-reading material (linked as **Text** above), and some executable Jupyter Notebooks, which are often specific to the framework (**PyTorch** or **TensorFlow**). The executable notebook also contains a lot of theoretical material, so to understand the topic you need to go through at least one version of the notebooks (either PyTorch or TensorFlow). There are also **Labs** available for some topics, which give you an opportunity to try applying the material you have learned to a specific problem. 
 
 Some sections also contain links to **MS Learn** modules that cover related topics. Microsoft Learn provides a convenient GPU-enabled learning environment, although in terms of content you can expect this curriculum to go a bit deeper.
 

lessons/5-NLP/14-Embeddings/README.md

@@ -21,7 +21,7 @@ By using embedding layer as a first layer in our classifier network, we can swit
 
 ## Semantic Embeddings: Word2Vec
 
-While embedding layer learnt to map words to vector representation, however, this representation did not necessarily have much semantical meaning. It would be nice to learn such vector representation that similar words or synonyms correspond to vectors that are close to each other in terms of some vector distance (eg. Euclidean distance).
+While embedding layer learned to map words to vector representation, however, this representation did not necessarily have much semantical meaning. It would be nice to learn such vector representation that similar words or synonyms correspond to vectors that are close to each other in terms of some vector distance (eg. Euclidean distance).
 
 To do that, we need to pre-train our embedding model on a large collection of text in a specific way. One of the first ways to train semantic embeddings is called [Word2Vec](https://en.wikipedia.org/wiki/Word2vec). It is based on two main architectures that are used to produce a distributed representation of words:
 

lessons/5-NLP/README.md

@@ -2,25 +2,25 @@
 
 ![Summary of NLP tasks in a doodle](../sketchnotes/ai-nlp.png)
 
-In this section, we will focus on using Neural Networks to handle tasks related to natural language processing (NLP). There are many NLP problems that we want computers to be able to solve:
+In this section, we will focus on using Neural Networks to handle tasks related to **Natural Language Processing (NLP)**. There are many NLP problems that we want computers to be able to solve:
 
-* **Text classification** is a typical classification problem on text sequences. Examples include classifying e-mail messages as spam vs. no-spam, or categorizing articles as sport, business, politics, etc. Also, when developing chat bots, we often need to understand what a user wanted to say -- in this case we are dealing with **intent classification**. Often, in intent classification we need to deal with many categories.
-* **Sentiment analysis** is a typical regression problem, where we need to attribute a number -- sentiment -- corresponding to how positive/negative the meaning of a sentence is. More advanced version of sentiment analysis is **aspect-based sentiment analysis** (ABSA), where we attribute sentiment not to the whole sentence, but to different parts of it (aspects), eg. *In this restaurant, I liked the cuisine, but the atmosphere was awful*.
+* **Text classification** is a typical classification problem pertaining to text sequences. Examples include classifying e-mail messages as spam vs. no-spam, or categorizing articles as sport, business, politics, etc. Also, when developing chat bots, we often need to understand what a user wanted to say -- in this case we are dealing with **intent classification**. Often, in intent classification we need to deal with many categories.
+* **Sentiment analysis** is a typical regression problem, where we need to attribute a number (a sentiment) corresponding to how positive/negative the meaning of a sentence is. A more advanced version of sentiment analysis is **aspect-based sentiment analysis** (ABSA), where we attribute sentiment not to the whole sentence, but to different parts of it (aspects), eg. *In this restaurant, I liked the cuisine, but the atmosphere was awful*.
 * **Named Entity Recognition** (NER) refers to the problem of extracting certain entities from text. For example, we might need to understand that in the phrase *I need to fly to Paris tomorrow* the word *tomorrow* refers to DATE, and *Paris* is a LOCATION.  
 * **Keyword extraction** is similar to NER, but we need to extract words important to the meaning of the sentence automatically, without pre-training for specific entity types.
 * **Text clustering** can be useful when we want to group together similar sentences, for example, similar requests in technical support conversations.
 * **Question answering** refers to the ability of a model to answer a specific question. The model receives a text passage and a question as inputs, and it needs to provide a place in the text where the answer to the question is contained (or, sometimes, to generate the answer text).
 * **Text Generation** is the ability of a model to generate new text. It can be considered as classification task that predicts next letter/word based on some *text prompt*. Advanced text generation models, such as GPT-3, are able to solve other NLP tasks such as classification using a technique called [prompt programming](https://towardsdatascience.com/software-3-0-how-prompting-will-change-the-rules-of-the-game-a982fbfe1e0) or [prompt engineering](https://medium.com/swlh/openai-gpt-3-and-prompt-engineering-dcdc2c5fcd29)
-* **Text summarization** is a technique when we want a computer to "read" long text, and summarize it in a few sentences.
+* **Text summarization** is a technique when we want a computer to "read" long text and summarize it in a few sentences.
 * **Machine translation** can be viewed as a combination of text understanding in one language, and text generation in another one.
 
 Initially, most of NLP tasks were solved using traditional methods such as grammars. For example, in machine translation parsers were used to transform initial sentence into a syntax tree, then higher level semantic structures were extracted to represent the meaning of the sentence, and based on this meaning and grammar of the target language the result was generated. Nowadays, many NLP tasks are more effectively solved using neural networks.
 
-Many classical NLP methods are implemented in [Natural Language Processing Toolkit (NLTK)](https://www.nltk.org) Python library. There is a great [NLTK Book](https://www.nltk.org/book/) available online that covers how different NLP tasks can be solved using NLTK.
+> Many classical NLP methods are implemented in [Natural Language Processing Toolkit (NLTK)](https://www.nltk.org) Python library. There is a great [NLTK Book](https://www.nltk.org/book/) available online that covers how different NLP tasks can be solved using NLTK.
 
 In our course, we will mostly focus on using Neural Networks for NLP, and we will use NLTK where needed.
 
-We have already learnt about using neural networks for dealing with tabular data and with images. The main difference between those types of data and text is that text is a sequence of variable length, while the input size in case of images is known in advance. While convolutional networks can extract patterns from input data, patterns in text are more complex. Eg., we can have negation being separated from the subject be arbitrary many words (eg. *I do not like organges*, vs. *I do not like those big colorful tasty oranges*), and that should still be interpreted as one pattern. Thus, to handle language we need to introduce new neural network types, such as *recurrent networks* and *transformers*.
+We have already learned about using neural networks for dealing with tabular data and with images. The main difference between those types of data and text is that text is a sequence of variable length, while the input size in case of images is known in advance. While convolutional networks can extract patterns from input data, patterns in text are more complex. Eg., we can have negation being separated from the subject be arbitrary for many words (eg. *I do not like oranges*, vs. *I do not like those big colorful tasty oranges*), and that should still be interpreted as one pattern. Thus, to handle language we need to introduce new neural network types, such as *recurrent networks* and *transformers*.
 
 ## Install Libraries
 
@@ -39,9 +39,9 @@ pip install -r requirements-tf.txt
 
 In this section, in some of the examples we will be training quite large models. It is advisable to run notebooks on GPU-enabled computer to minimize waiting time.
 
-When running on GPU, you may experience situations when you run out of GPU memory. During training, the amount of GPU memory consumed depends on many factors, including minibatch size. If you experience any memory problems - you may try to minimize the minibatch size in the code.
+When running on GPU, you may experience situations when you run out of GPU memory. During training, the amount of GPU memory consumed depends on many factors, including the minibatch size. If you experience any memory problems - you may try to minimize the minibatch size in the code.
 
-Also, some older versions of TensorFlow do not release GPU memory correctly if we are training multiple models in one Python kernel. In order to use GPU memory cautiously, you may set TensorFlow option to grow GPU memory allocation only when required. You would need to include the following code in your notebooks:
+Also, some older versions of TensorFlow do not release GPU memory correctly if you are training multiple models in one Python kernel. In order to use GPU memory cautiously, you may set TensorFlow option to grow GPU memory allocation only when required. You would need to include the following code in your notebooks:
 
 ```python
 physical_devices = tf.config.list_physical_devices('GPU') 

lessons/7-Ethics/README.md

@@ -4,7 +4,7 @@ You have almost finished this course, and I hope that by now you clearly see tha
 
 However, in science fiction we often see stories where AI presents a danger to the humankind. Usually those stories are centered around some sort of AI rebellion, when AI decides to confront human beings. This implies that AI has some sort of emotions, or can take decisions unforeseen by its developers.
 
-The kind of AI that we have learnt about in this course is nothing more than large matrix arithmetics. It is a very powerful tool to help us solve our problems, and as any other powerful tool - it can be used for good and for bad purposes. What's also important, it can be *misused*.
+The kind of AI that we have learned about in this course is nothing more than large matrix arithmetics. It is a very powerful tool to help us solve our problems, and as any other powerful tool - it can be used for good and for bad purposes. What's also important, it can be *misused*.
 
 ## Principles of Responsible AI