2020 Fall, BME Department of Automation and Applied Informatics
Instructors
- Judit Ács
- Ádám Kovács
- Kinga Gémes
Administrative and technical questions should be directed to Judit Acs (acs DOT judit AT aut DOT bme DOT hu)
Official course syllabus and requirements (TAD)
Previous offerings
Schedule
Week | Lecture | Lab | Deadlines | |||
---|---|---|---|---|---|---|
1 | Sept 9 | Introduction: what is natural language processing, typical applications, history, major areas | Sept 10 | Setting up, git repository, basic exercises, NLP tools | - | |
2 | Sept 16 | Built-in types, functions | Sept 17 | Using Jupyter. Writing simple functions. Handling text files. | - | |
3 | Sept 23 | Built-in types in details. Advanced string manipulations, regular expressions. | Sept 24 | Typical string manipulation exercises. Writing a simple parser with regular expressions. | - | |
4 | Sept 30 | Object-oriented Python, properties, static methods, class methods, magic methods, operator overloading. Iterators, generators. Context managers. | Oct 1 | complex OOP exercises | - | |
5 | Oct 7 | Decorators. Functional programming in Python. Writing command line applications in Python. Using Linux command line applications for text processing. IO redirection, pipelines. | Oct 8 | Writing a simple command line application. Using it in the terminal, interacting with built-in Linux commands via pipes. | - | |
6 | Oct 14 | Scientific Python. Numpy, scipy. Basic matrix operations. Sparse matrices. | Oct 15 | Matrix manipulation. Working with large sparce matrices. | - | |
7 | Oct 21 | NO CLASS | Oct 22 | NO CLASS | - | |
8 | Oct 28 | Data science. Handling text data. Basic shell commands. Pandas. | Oct 29 | Handling text data exercises. Data cleaning. Pandas exercisesevaluation loops | - | |
9 | Nov 4 | Deep learning for NLP. Feed forward neural networks, recurrent neural networks. LSTM, GRU. | Nov 5 | PyTorch basics. Defining neural networks, training and evaluation loops | ||
10 | Nov 11 | NO CLASS | Nov 12 | NO CLASS | - | |
11 | Nov 18 | Textual sequence modeling: sequence labeling and classification, sequence-to-sequence models. Attention. | Nov 19 | Sequence modeling in PyTorch. | - | |
12 | Nov 25 | Language modeling. Word vectors. Contextualized language models. Transformers. BERT. | Nov 26 | Exploring pretrained models: word2vec, GloVe, fastText, BERT, ELMo | - | |
13 | Dec 2 | Dependency parsing. Universal dependencies. | Dec 3 | Working with Universal Dependencies. Multilingual models and problems. | - | |
14 | Dec 9 | NLP applications | Dec 10 | Final project presentations | - | |