fact verification model(FVM) is trained on FEVER, which aims to predict the veracity of a textual claim against a trustworthy knowledge source such as Wikipedia.
This repo hosts the following models for FVM:
fact_checking/: the verification models based on BERT (large) and RoBERTa (large), respectively.mrc_seq2seq/: the generative machine reading comprehension model based on BART (base).evidence_retrieval/: the evidence sentence ranking models, which are copied directly from KGAT.