# Structured Data Reasoning

BnTQA-mBart is a low-resource Bengali table question answering model based on the mBART architecture, specifically designed for handling Bengali structured table data question answering tasks.

TAPEX is a model designed for table question answering tasks, learning table pre-training through neural SQL executors and based on the BART architecture.

TAPAS is a pre-trained language model based on tabular data, specifically designed for natural language tasks related to tables.

TAPAS is a BERT-like model based on the Transformer architecture, specifically designed for processing tabular data. It is pre-trained in a self-supervised manner on English Wikipedia table data and fine-tuned on the TabFact dataset to determine whether a sentence is supported or refuted by table content.