Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning - code

We train embedding spaces with the MFTC corpus, to see how an embedding space can learn the distribution of pluralist morality. We compare off-the-shelf, unsupervised, and supervised approaches, showing that a supervised approach is necessary. Here, you can find the code used to train and evaluate the resulting embedding spaces.