Variational Open-Domain Question Answering
share
We introduce the Variational Open-Domain (VOD) framework for end-to-end training and evaluation of retrieval-augmented models (open-domain question answering and language modelling). We show that the Rényi variational bound, a lower bound to the task marginal likelihood, can be exploited to aid optimization and use importance sampling to estimate the task log-likelihood lower bound and its gradients using samples drawn from an auxiliary retriever (approximate posterior). The framework can be used to train modern retrieval-augmented systems end-to-end using tractable and consistent estimates of the Rényi variational bound and its gradients. We demonstrate the framework's versatility by training reader-retriever BERT-based models on multiple-choice medical exam questions (MedMCQA and USMLE). We registered a new state-of-the-art for both datasets (MedMCQA: 62.9%, USMLE: 55.0%). Last, we show that the retriever part of the learned reader-retriever model trained on the medical board exam questions can be used in search engines for a medical knowledge base.
READ FULL TEXT
