Theory: Linear Algebra, Analytic Geometry, Matrix decompositions, Vector Calculus, Probability and Distributions, Continuous Optimization. Refer Chapters 1-7 from the MML book.
Programming: Python: Source, Pytorch: Source.
Software and Packages: Anaconda, Jupyter notebook, NLTK.
Dan Jurafsky and James H. Martin. Speech and Language Processing (3rd ed. draft).
Jacob Eisenstein. Natural Language Processing.
Christopher Manning and Hinrich Schutze. Foundations of Statistical Natural Language Processing.
| Class | Topic | Reading | Notebooks and Assignments |
|---|---|---|---|
| 1-2 | Introduction, Mathematical Preliminaries | ||
| 3-4 | Basic Text Processing, Edit distance | ||
| 5 | Linear Text Classification | ||
| 6-7 | Word Embeddings | ||
| 7-9 | Language models, spelling correction | ||
| 10-11 | Neural Networks and Neural Language Models | ||
| 12-15 | Deep Learning Architectures for Sequence Processing | ||
| 16-18 | Sequence labelling POS tagging, NER, Tokenization | ||
| 19-21 | Parsing | ||
| 22-24 | Machine Translation | ||
| 25-27 | Semantics | ||
| 28-29 | Reference resolution, Discourse (Entity Linking) | ||
| 30-31 | Question Answering | ||
| 32-33 | Summarization | ||
| 34 | Dialogue Systems | ||
| 35-36 | Sentiment Analysis | ||
| 37-38 | Ethics |