This repository contains the code for the paper "Counterfactual Reasoning with Knowledge Graph Embeddings" to be presented at EACL 2024.
Note that most of the code is built upon the CoDEx (https://github.com/tsafavi/codex) and LibKGE (https://github.com/uma-pi1/kge) repositories (both licensed under the MIT License). To run the code, please follow the instructions on the CoDEx repository to set up the environment. Then move the files and folders in this project into the resulting "codex" folder, and train_adapted_couldd.py into kge/kge/job.
If you have any questions, please reach out.
This research has been funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) RO 5127/2-1 and the Vienna Science and Technology Fund (WWTF)[10.47379/VRG19008] ”Knowledge-infused Deep Learning for Natural Language Processing”.