KNOWLEDGE_INFOTABS
INFOTABS
TempTabQA
To truly grasp reasoning ability, a Natural Language Inference model should be evaluated on counterfactual data. TabPert facilitates this by assisting in the generation of such counterfactual data for assessing model tabular reasoning issues. TabPert allows a user to update a table, change its associated hypotheses, change their labels, and highlight rows that are important for hypothesis classification. TabPert also captures information about the techniques used to automatically produce the table, as well
tl;dr : TabPert is a tool to augment existing tabular datasets to effectively and efficiently create counterfactual datasets.
Existing NLI models tend to exploit annotation artefacts, pre-trained knowledge, and hypothesis biases in data to answer a premise. Therefore, to test their performance effectively, we must test them on adversarial data , on which their performance significantly reduces. However, perturbing existing tabular datasets to create counterfactual data is difficult and inefficient without specialised tools. This is where TabPert comes in!
KNOWLEDGE_INFOTABS
INFOTABS
TempTabQA