Code for the Stanford course.
Spring 2023
Details on how to get set up to work with this code.
The set of homeworks for the current run of the course.
Introductions to Jupyter notebooks, scientific computing with NumPy and friends, and PyTorch.
A generic optimization class (torch_model_base.py) and subclasses for GloVe, Autoencoders, shallow neural classifiers, RNN classifiers, tree-structured networks, and grounded natural language generation.
tutorial_pytorch_models.ipynb shows how to use these modules as a general framework for creating original systems.
Notebooks covering key experimental methods and practical considerations, and tips on writing up and presenting work in the field.
Part of our unit on explainability and model analysis.
This is now considered background material for the course.
Reference implementations for the torch_*.py models, designed to reveal more about how the optimization process works.
This is now considered background material for the course.
A unit on vector space models of meaning, covering traditional methods like PMI and LSA as well as newer methods like Autoencoders and GloVe. vsm.py provides a lot of the core functionality, and torch_glove.py and torch_autoencoder.py are the learned models that we cover. vsm_03_contextualreps.ipynb explores methods for deriving static representations from contextual models.
This is now considered background material for the course.
A unit on sentiment analysis with the English Stanford Sentiment Treebank. The core code is sst.py, which includes a flexible experimental framework. All the PyTorch classifiers are put to use as well: torch_shallow_neural_network.py, torch_rnn_classifier.py, and torch_tree_nn.py.
This is now considered background material for the course.
Using pretrained parameters from Hugging Face for featurization and fine-tuning.
Miscellaneous core functions used throughout the code.
To run these tests, use
py.test -vv test/*
or, for just the tests in test_shallow_neural_classifiers.py,
py.test -vv test/test_shallow_neural_classifiers.py
If the above commands don't work, try
python3 -m pytest -vv test/test_shallow_neural_classifiers.py
The materials in this repo are licensed under the Apache 2.0 license and a Creative Commons Attribution-ShareAlike 4.0 International license.