Stanford - Winter 2023
These are my solutions for the CS224N course assignments offered by Stanford University (Winter 2023). Written questions are explained in detail, the code is brief and commented. These solutions are heavily inspired by mantasu's repo and floriankark's repo.
For conda users, the instructions on how to set-up the environment are given in the handouts. For pip users, I've gathered all the requirements in one file. Please set up the virtual environment and install the dependencies (for linux users):
$ python -m venv venv
$ source venv/bin/activate
$ pip install -r requirements.txtYou can install everything with conda too (see this). For code that requires Azure Virtual Machines, I was able to run everything successfully on Google Colab with a free account.
Note: Python 3.8 or newer should be used
For every assignment, i.e., for directories assigment1 through assignment5, there is coding and written parts. The solutions.pdf files are generated from latex directories where the provided templates were filled while completing the questions in handout.pdf files and the code.
- A1: Exploring Word Vectors (Done)
- A2: word2vec (Done)
- A3: Dependency Parsing (Done)
- A4: Neural Machine Translation with RNNs and Analyzing NMT Systems (Done)
- A5: Self-Attention, Transformers, and Pretraining (Done)
- Complete the minBERT project.