The source code of paper "Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction"
For training, a GPU is recommended to accelerate the training speed.
The code is based on PyTorch 1.6+. You can find tutorials here.
The dependencies are summarized in the file requirements.txt.
You can install these dependencies like this:
pip3 install -r requirements.txt
You also need to install Horovod and Apex
- Run the full model on NewsCLIPpings dataset with default hyperparameter settings
sh run.sh
- NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media (access)