STEPS is an end-to-end approach for producing user intent in terms of actions and objects only, dispensing with the need for their definitions. This is achieved by reformulating the free-form Multi-axis Event Process Typing task as a sequence generation problem.

If you find our paper, code or framework useful, please reference this work in your paper:

@inproceedings{pepe-etal-2022-steps,
  title     = {STEPS: Semantic Typing of Event Processes with a Sequence-to-Sequence Approach},
  author    = {Pepe, Sveva and Barba, Edoardo, and Blloshmi, Rexhina and Navigli, Roberto},
  booktitle = {Proceedings of {AAAI}},
  year      = {2022},
}

Requirements:

• Debian-based (e.g. Debian, Ubuntu, ...) system
• conda

We strongly advise utilizing the bash script setup.sh to set up the python environment for this project. Run the following command to quickly setup the env needed to run our code:

bash ./setup.sh

It's a bash command that will setup a conda environment with everything you need. Just answer the prompts as you proceed.

• Checkpoint of STEPS will be released soon!

Training is done via the training script, src/train.py, and its parameters are read from the .yaml files in the conf/ folders. Once you applied all your desired changes, you can run the new training with:

(steps) user@user-pc:~/steps$ PYTHONPATH=$(pwd) python src/train.py

If you want to evaluate the model you just have to run the following command:

(steps) user@user-pc:~/steps$ PYTHONPATH=$(pwd) python src/predict.py --ckpt <steps_checkpoint.ckpt>

This project is released under the CC-BY-NC-SA 4.0 license (see LICENSE). If you use STEPS, please put a link to this repo.

The authors gratefully acknowledge the support of the ERC Consolidator Grant MOUSSE No. 726487 and the ELEXIS project No. 731015 under the European Union’s Horizon 2020 research and innovation programme.

This work was supported in part by the MIUR under the grant "Dipartimenti di eccellenza 2018-2022" of the Department of Computer Science of the Sapienza University of Rome.