Code and slides to accompany the online lecture series (https://bit.ly/NLP_LL_v3) by Data For Science.
Natural Language Processing LiveLessons covers the fundamentals and some of the more advanced aspects of Natural Language Processing in a simple and intuitive way, empowering you to add NLP to your toolkit. Using the powerful NLTK package, it gradually moves from the basics of text representation, cleaning, topic detection, regular expressions, and sentiment analysis before moving on to the PyTorch deep learning framework to explore advanced topics such as text classification and sequence-to-sequence models. The transformer architectures underlying Large Language Models (LLMs) like ChatGPT, Claude and BERT are explored in depth along with some practical applications. After successfully completing these lessons you'll be equipped with a fundamental and practical understanding of the full breath of Natural Language Processing tools and algorithms.
- One-hot Encoding
- Bag of Words
- Stopwords
- TF/IDF
- N-grams
- Word Embeddings
- Stemming
- Lemmatization
- Regular Expressions
- Part Of Speech Tagging
- Chunking
- Chinking
- Named Entity Recognition
- Explicit Semantic Analysis
- Document Clustering
- Latent Semantic Analysis
- Latent Dirichlet Allocation
- Non-Negative Matrix Factorization
- Quantifying Words and Feelings
- Negations and Modifiers
- Corpus Based Approaches
- Feed-Forward Networks
- Convolutional Neural Networks
- Applications
- Recurrent Neural Networks (RNN)
- Gated Recurrent Unit (GRU)
- Long-Short Term Memory (LSTM)
- Auto-Encoder Models
- word2vec Embeddings
- GloVe
- Transfer Learning
- Language Detection
- Large Language Models
- Transformers
- BERT
- HuggingFace
- NLP Tasks