lysandre/tapas-temporary-repo

TAPAS is a BERT-like transformers model pretrained on a large corpus of English data from Wikipedia in a self-supervised fashion . The model was pre-trained on MLM and an additional step which the authors call intermediate pre-training, and then fine-tuned on SQA . It uses relative position embeddings by default (i.e. resetting the position index at every cell of the table) The model can be used to answer questions about a table, or determine whether a sentence is supported or refuted by the contents of a table . It can also be used for answering questions related to a table in a conversational set-up,