RelEx

A simple framework for Relation Extraction built on AllenNLP.

---

🔭  Overview

Path	Description
configs/	This directory contains model configurations for relation classification.
scripts/	This directory contains scripts, e.g., for evaluating a model with a dataset-specific scorer.

✅  Requirements

RelEx is tested with:

• Python 3.7

🚀  Installation

With pip

<TBD>

From source

git clone https://github.com/DFKI-NLP/RelEx
cd RelEx
pip install .

🔧  Usage

Training

allennlp train \
    ./configs/relation_classification/tacred/baseline_cnn_tacred.jsonnet \
    -s <RESULTS DIR> \
    --include-package relex

👾  Models

Model	Link	Description
	[Link]

📚  Citation

@misc{alt-etal-2020-relex,
  author = {Christoph Alt and Marc H\"{u}bner and Leonhard Hennig},
  title = {RelEx},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/DFKI-NLP/RelEx}}
}

Also, please consider cite the following paper when using RelEx:

@inproceedings{alt-etal-2020-probing,
    title={Probing Linguistic Features of Sentence-level Representations in Neural Relation Extraction},
    author={Christoph Alt and Aleksandra Gabryszak and Leonhard Hennig},
    year={2020},
    booktitle={Proceedings of ACL},
    url={https://arxiv.org/abs/}
}

📘  Licence

RelEx is released under the terms of the Apache 2.0 License.