Intro to NLP Course

⚠️ 🚧 This course is currently in an ongoing state. It will be entirely available as soon as the current classes finish. 🚧 ⚠️

Welcome to our introductory course on Natural Language Processing (NLP)!

NLP is a multidisciplinary field that brings together computer science, artificial intelligence, linguistics, and even cognitive psychology. It allows machines to understand, interpret, generate, and respond to human text and speech, bridging the gap between human communication and computer understanding.

During this course, we will delve into the core principles of NLP, covering topics such as:

Tokenization: Splitting text into words, phrases, symbols, or other meaningful elements.
Text Preprocessing: Techniques to clean and prepare text data for analysis, including stemming and lemmatization.
Word Embeddings: How to represent words in numerical formats that capture semantic meanings.
Syntax and Parsing: Understanding the grammatical structure of sentences.
Sentiment Analysis: Detecting emotions and opinions within the text.
Machine Translation: Automatically translating text between languages.

Section	Links	About
Naïve-Bayes	slides, quiz	An overview of the Naïve-Bayes algorithm and how it can be used for sentiment analysis and as a language model.
Logistic Regression	slides	We compare Logistic Regression with Naïve-Bayes (Discriminative x Generative) and introduce the basic reasoning behind TF-IDF.
Word Embeddings	slides	Introduction to word vectors, vector spaces and similarity. Using word embedding for machine translation.
Language Models (Theory)	slides	Introductions to language models and the theory behind them.
Language Models on Neural Networks	slides	Language models on Neural Networks: how word embeddings are trained, CBOW.
NLP with Tensorflow (Practical Examples)	slides examples	Examples on how to run basic NLP examples on Tensorflow: data processing, tokenization, sentiment analysis.