Visão Geral

O Curso Natural Language Processing using Deep Learning, é adequado para quem deseja aprender como processar e compreender texto. Abrange as arquiteturas mais populares, incluindo Redes Neurais Recorrentes e Modelos Ocultos de Markov. Seria preferível fazer o curso Básico de Aprendizado de Máquina com antecedência para que o aluno se acostumasse com o vocabulário e os principais frameworks.

Materiais

Conteúdo Programatico

NLP applications
Word vectors

1. What are vectors?
2. Word analogies
3. TF-IDF and t-SNE
4. NLTK
5. GloVe
6. Word2vec
7. Text classification using word vectors

Hands-on Lab:

1. Performing a basic text classification using multiple word vectors models
2. Improve it by using basic text processing and language models to get the data ready for machine learning

Language modeling

1. Bigrams
2. Language models
3. Neural Network Bigram Model

Hands-on Lab:

1. Performing text classification using neural networks based on language models
2. Understand the probabilistic modeling of language model, how to improve the context of a word and how synonyms can be generated and how basic neural networks generate powerful language models

Word Embeddings

1. CBOW
2. Skip-Gram
3. Negative Sampling

Hands-on Lab: Understand advanced techniques for language modeling like Skip-Gram and Negative Sampling by implementing them and learn to predict the next most likely word in a conversation

NLP techniques

1. What is POS Tagging?
2. POS Tagging Recurrent Neural Network
3. POS Tagging Hidden Markov Model (HMM)
4. Named Entity Recognition (NER)
5. POS vs. NER

Hands-on Lab: Use NLTK and SCIPY to improve your classification using grammar rules and POS, then use NER to highlight the most valuable content of a phrase, afterwards implement summarization
 

Recurrent Neural Networks

1. LSTM
2. GRU
3. Text Generation

Hands-on Lab:

1. Implement in Keras a basic RNN architecture for word prediction, using the already studied word embeddings
2. Benchmark the performances of LSTM compared to GRU and BiLSTM

Generative Neural Networks
Hands-on Lab:

1. Implement in Keras your own generative model that generates lyrics similar to the ones from Shakespeare
2. Learn to make Transfer Learning on text