trokhymovych/wikicheck

Implementation for WikiCheck API, an open-source Wikipedia-based fact-checking API. The project is done in cooperation with Wikimedia Foundation and Ukrainian Catholic University.

WikiCheck API

Repository with the implementation of WikiCheck API, end-to-end open source Automatic Fact-Checking based on Wikipedia.

The research was published in CIKM2021 applied track:

• Trokhymovych, Mykola, and Diego Saez-Trumper. WikiCheck: An End-to-End Open Source Automatic Fact-Checking API Based on Wikipedia. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Association for Computing Machinery, 2021, pp. 4155–4164, CIKM ’21.

• The preprint WikiCheck: An End-to-End Open Source Automatic Fact-Checking API Based on Wikipedia:

We encourage you to test the WikiCheck API by yourself:

Installation and Usage:

The project consists of modules directory with the implementation of modules used for inference along with the script for NLI models training.

The configs directory includes configuration files for training and inference.

The notebooks directory includes .ipynb notebooks with experiments done during the research.

If you want to get access to our fine-tuned models, you can load them from Zenodo

Also, you can train your model by running the modules/model_trainer.py script.

API setup and run

• Clone the official WikiCheck repo and cd into it

git clone https://github.com/trokhymovych/WikiCheck.git

cd WikiCheck

• Create and activate virtualenv:

virtualenv -p python venv

source venv/bin/activate

• Install requirements from requirements.txt:

pip install -r requirements.txt

• Load pretrained models:

  • Loading models from Zenodo

• Run the API:

python run.py --config configs/inference/sentence_bert_config.json

Citation

If you find this work is useful, please cite our paper:

WikiCheck: An End-to-End Open Source Automatic Fact-Checking API Based on Wikipedia.

@inproceedings{10.1145/3459637.3481961,
author = {Trokhymovych, Mykola and Saez-Trumper, Diego},
title = {WikiCheck: An End-to-End Open Source Automatic Fact-Checking API Based on Wikipedia},
year = {2021},
isbn = {9781450384469},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3459637.3481961},
doi = {10.1145/3459637.3481961},
booktitle = {Proceedings of the 30th ACM International Conference on Information & Knowledge Management},
pages = {4155–4164},
numpages = {10},
keywords = {applied research, nlp, nli, wikipedia, fact-checking},
location = {Virtual Event, Queensland, Australia},
series = {CIKM '21}
}