The Question Answering task in NLP pertains to building a model which can answer questions posed in natural language. Many datasets (including SQuAD, the dataset we use in this notebook) pose this as a reading comprehension task i.e. given a question and a context, the goal is to predict the span within the context with a start and end position which indicates the answer to the question. For every word in the training dataset we predict:
1.likelihood this word is the start of the span
2.likelihood this word is the end of the span
The best place to get started with TAO Toolkit - Question Answering would be the TAO - Question Answering jupyter notebook. The notebook shows Sample workflow for training a question answering model and export the model to a .riva file For more information check TAO Toolkit product page - https://developer.nvidia.com/tao-toolkit