This series of modules introduces learners to natural language processing (NLP).
Check back soon for more details.
Learning Objectives
- Enumerate various applications of NLP technology
- Perform basic data cleaning tasks, including tokenization, case normalization, punctuation, stop word removal, and stemming and lemmatization.
- Describe the classical approaches to text representation
- Implement one-hot encoding, term frequencies, and the TD-IDF method in code.
- Describe the basic workings of word embeddings (vector) algorithms
- Implement the Word2Vec algorithm in code
- Discuss the function of the various Word2Vec hyperparameters
- Recognize that a given text data set may contain implicit bias
