NLP and LLMs - Foundations of NLP
About
NLP foundations introduces various ways to represent text numerically including word vectors and text embeddings.
Learning Objectives
You will be able to:
- Define common use cases for text data.
- Describe the evolution of text representation from traditional methods to embeddings.
- Apply CountVectorizer, TF-IDF to complete a sentiment analysis of customer reviews.
- Compare two embedding methods, Word2Vec and BERT, using customer reviews.
- Discuss real-world considerations for embedding selection.
Content
| Topic | About |
|---|---|
| Full Lesson Deck | To be used for the full session, includes the labs below |
| text-frequency.ipynb | First code-a-long and mini-lab |
| embeddings.ipynb | Second code-a-long |
Prerequisites
- Write and run Python code in a Jupyter notebook.
- Create basic Python functions.
- Import and use
pandasandnumpy. - Understand, run, and evaluate classification models and metrics in
scikit-learn, in particular logistic regression.
References
📖 Reference Materials
Important note
Please ignore the _layouts folder and the config.yml file in the root of this repo. They are needed to make sure the repo renders well; please don’t change them or delete them and your repo will work fine :)