We are fine-tuning a transformer-based question answering model to answer the questions about the novels with the chronological plot. We are breaking up the novel into chapters and then using them as contexts with questions and answers, following the SQuAD 2.0 model

Our model is a customized HuggingFace DistilBERT.

My question - is such QA model capable of learning across contexts, so that it associates, for example, relationships between protagonists and places that do not necessarily all appear in the same contexts?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.