DATA 441/641: Applied Natural Language Processing
This is a complementary course hub. Canvas is the official site for this semester. Questions: mousavi@american.edu.
Syllabus
Class meetings
Thursday class meetings, 5:30–8:00 PM. Canvas is official for submissions and any date changes.
| Week | Topic | Notes |
|---|---|---|
| 1 | NLP in the real world and Python | |
| 2 | Data acquisition and preprocessing | |
| 3 | Feature engineering, modeling, and evaluation | |
| 4 | Text representation | |
| 5 | Deep learning and Word2Vec | |
| 6 | Text classification | |
| 7 | CNNs for text | |
| 8 | Recurrent neural networks | |
| 9 | Midterm review | Midterm |
| 10 | Information extraction | |
| 11 | Named entity recognition | |
| 12 | Chatbots and dialog systems | |
| 13 | SVD and topic modeling | |
| 14 | LDA and NMF topic models | |
| 15 | Summarization, translation, and recommenders |
Weekly materials
Open a week for its lectures, labs, readings, and discussion prompts. Canvas remains the official list of required reading.
Data
| Dataset | Files |
|---|---|
| COVID-19 tweets | covid19_tweets.csv |
| Fake news | fakeNews.csv |
| Nemo | nemo.txt |
| Sample PDF | sample.pdf |
| Spam | spam.csv |
| Train labels | TrainLabels.csv |
| True news | trueNews.csv |
Resources
| Resource | What it is for |
|---|---|
| Python | Install Python |
| Jupyter | Notebooks for labs |
| NLTK | Classic NLP toolkit |
| Practical Natural Language Processing | Main textbook (Vajjala, Majumder, Gupta, Surana) |
| Deep Learning with Python | Neural nets (Chollet) |