Visão Geral
O curso Introduction to Natural Language Processing in Python apresenta os fundamentos do Processamento de Linguagem Natural (NLP), uma das áreas mais fascinantes e aplicadas da Inteligência Artificial. O participante aprenderá como usar Python e suas principais bibliotecas para processar, analisar e compreender textos, explorando técnicas de tokenização, stemming, lematização, modelagem de tópicos e análise de sentimentos.
Conteúdo Programatico
Introduction to Natural Language Processing
- What is NLP and why it matters
- Applications of NLP in business and technology
- Overview of text-based AI systems
Setting Up the Environment
- Installing Python NLP libraries (NLTK, spaCy, TextBlob)
- Jupyter Notebook setup and data sources
Text Preprocessing Techniques
- Tokenization and sentence segmentation
- Stop words removal
- Stemming and Lemmatization
Text Normalization and Representation
- Bag-of-Words (BoW) and TF-IDF models
- Word embeddings introduction (Word2Vec, GloVe)
- Vectorization and feature extraction
Exploratory Text Analysis
- Frequency analysis and word clouds
- N-grams and co-occurrence analysis
- Visualizing textual data
Sentiment Analysis
- Rule-based and machine learning approaches
- Implementing sentiment classifiers with TextBlob and scikit-learn
- Evaluating sentiment models
Topic Modeling and Text Classification
- Introduction to Latent Dirichlet Allocation (LDA)
- Training and evaluating text classification models
- Multi-class classification with Naive Bayes and SVM
Named Entity Recognition (NER) and POS Tagging
- Using spaCy for entity and part-of-speech tagging
- Extracting entities from text corpora
Building Simple NLP Applications
- Creating a sentiment analysis web app with Streamlit
- Chatbot basics with rule-based NLP
Future of NLP and Ethical Considerations
- Deep learning in NLP (BERT, Transformers overview)
- Challenges and ethical aspects of language models