---
license: mit
tags:
- automated-planning
- masked-language-modeling
- bert
---

# BERT for Automated Planning (Driverlog)

This is a BERT model pretrained on Masked Language Modelling (MLM), specifically developed to tackle tasks related to Automated Planning within the Driverlog domain. 

You can find its full description, methodology, and experimental results in our paper: **[A Preliminary Study on BERT applied to Automated Planning](https://ceur-ws.org/Vol-3345/paper7_3460.pdf)**.

## Usage

You can easily load the model and the tokenizer using the Hugging Face `transformers` library:

```python
from transformers import BertForMaskedLM, PreTrainedTokenizerFast

tokenizer = PreTrainedTokenizerFast.from_pretrained("lore-seri97/bert-driverlog")
model = BertForMaskedLM.from_pretrained("lore-seri97/bert-driverlog")

```

## Citation

If you use this model in your research, please cite our work using the following BibTeX entry:

```bibtex
@inproceedings{DBLP:conf/aiia/SerinaCGPS22,
  author       = {Lorenzo Serina and
                  Mattia Chiari and
                  Alfonso Emilio Gerevini and
                  Luca Putelli and
                  Ivan Serina},
  editor       = {Riccardo De Benedictis and
                  Nicola Gatti and
                  Marco Maratea and
                  Andrea Micheli and
                  Aniello Murano and
                  Enrico Scala and
                  Luciano Serafini and
                  Ivan Serina and
                  Alessandro Umbrico and
                  Mauro Vallati},
  title        = {A Preliminary Study on {BERT} applied to Automated Planning},
  booktitle    = {Proceedings of the 10th Italian workshop on Planning and Scheduling
                  {(IPS} 2022), {RCRA} Incontri {E} Confronti (RiCeRcA 2022), and the
                  workshop on Strategies, Prediction, Interaction, and Reasoning in
                  Italy {(SPIRIT} 2022) co-located with 21st International Conference
                  of the Italian Association for Artificial Intelligence (AIxIA 2022),
                  November 28 - December 2, 2022, University of Udine, Udine, Italy},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {3345},
  publisher    = {CEUR-WS.org},
  year         = {2022},
  url          = {[https://ceur-ws.org/Vol-3345/paper7](https://ceur-ws.org/Vol-3345/paper7)\_3460.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:23:01 +0100},
  biburl       = {[https://dblp.org/rec/conf/aiia/SerinaCGPS22.bib](https://dblp.org/rec/conf/aiia/SerinaCGPS22.bib)},
  bibsource    = {dblp computer science bibliography, [https://dblp.org](https://dblp.org)}
}

```

---