/transformers-retrieval-ranking-nli-ECIR2021

Multilingual retrieval, ranking and natural language inference with transformers (mBERT); PyTorch implementation code for article in European Conference on Information Retrieval (ECIR2021)

Primary LanguagePythonApache License 2.0Apache-2.0

PyTorch Codebase for the article

Multilingual Evidence Retrieval, Ranking and Natural Language Inference

Requires up to 3Gb RAM. Fine-tuned models will be downloaded from S3; please email for access to models and datasets.

To cite:

@inproceedings{olteanu2021multilingual,
  title={Multilingual Evidence Retrieval and Fact Verification to Combat Global Disinformation: The Power of Polyglotism},
  author={Olteanu Roberts, Denisa A},
  booktitle={European Conference on Information Retrieval},
  pages={359--367},
  year={2021},
  organization={Springer}
}