| Unit | Topic | Readings & Resources |
Configuring your development environment | - Using Virtualbox to install a Linux VM
- version control with Git and GitHub
- Linux command line basics
- Containers with Docker
- Jupyter
| Unit tutorials |
NLP Intro | Syllabus, class overview, etc. Intro to ... - tokenization
- normalization
- POS Tagging
- NER
- syntactic representations
- coreference resolution
| Complete https://spacy.io/usage/spacy-101 Speech and Language Processing 2.4 Speech and Language Processing 8.0 - 8.2 Speech and Language Processing 18.1.0 - 18.1.1 Speech and Language Processing 22.1 Speech and Language Processing 12.0 - 12.1 Speech and Language Processing 15.0 - 15.1 |
ML Intro | - probability review
- classification using Naïve Bayes
- evaluating classifiers
| Speech and Language Processing 3.4.0 - 3.4.1 Speech and Language Processing 4.0 - 4.9 |
Logistic Regression | - logistic regression (overview)
- cross entropy
- MLE
- gradient descent
- regularization
- multinomial LR
| Speech and Language Processing 5.0 - 5.7 OPTIONAL: Speech and Language Processing 5.8 |
Word and Phrase Representations | - words as vectors
- TF-IDF
- PPMI
- lexical semantics and vector semantics
- word2vec (Skip-gram and CBOW)
- GloVe
- evaluating embeddings
| Speech and Language Processing Ch 6 Glove: Global Vectors for Word Representation The Illustrated BERT, ELMo, and co. Word embeddings demo |
Sequence Tagging | - part-of-speech tagging
- HMMs
- MEMMs
- decoding
| Speech and Language Processing 8.0 - 8.7 |
Dependency Parsing | - dependency trees
- transition-based parsing
- graph-based parsing
| Speech and Language Processing Ch 15 |
