Natural Language Processing (NLP) Fundamentals by Pearson

This course covers the fundamentals and some of the more advanced aspects of natural language processing (NLP). Are you ready to add NLP to your toolkit? Using the powerful NLTK package, explore the basics of text representation, cleaning, topic detection, regular expressions, and sentiment analysis before moving on to the PyTorch deep learning framework, text classification, and sequence-to-sequence models. Learn more about the transformer architectures underlying large language models (LLMs) like ChatGPT, Claude, and BERT. By the end of this course, you’ll be equipped with practical skills to leverage the extensive power of NLP tools and algorithms.

An ideal fit for data scientists with an interest in natural language processing, this course requires a working knowledge of basic algebra, calculus, and statistics, as well as basic programming experience.

Learning objectives
Implement text tokenization and representation.
Use one-hot encodings and bag of words.
Identify relevant words by applying TF-IDF.
Clean text through stemming and lemmatization techniques.
Match patterns using regular expressions.
Understand named entity recognition.
Cluster documents and model topics using various algorithms.
Conduct sentiment analysis, including handling negations and modifiers.
Utilize word embeddings for capturing semantic relationships.
Define GloVe.
Model sequences in PyTorch with RNNs, GRUs, and LSTM networks.
Transfer learning.
Apply language detection.
Understand and apply transformers.
Use LLMs for NLP tasks.
Build practical NLP applications with Hugging Face and large language models.