# Table Fact Verification

TAPAS is a BERT-based Transformer model specifically designed for processing tabular data. It is pre-trained on English Wikipedia tables through self-supervised learning and fine-tuned on the TabFact dataset to verify whether a sentence is supported or refuted by table content.

TAPEX is a table pre-training model learned through a neural SQL executor, based on the BART architecture, specifically designed for table reasoning tasks.

TAPEX is a model that learns table reasoning capabilities through neural SQL executor training.