Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering. (arXiv:2204.04581v2 [cs.CL] UPDATED)

Web: http://arxiv.org/abs/2204.04581

Retrieval augmented language models have recently become the standard for
knowledge intensive tasks. Rather than relying purely on latent semantics
within the parameters of large neural models, these methods enlist a
semi-parametric memory to encode an index of knowledge for the model to
retrieve over. Most prior work has employed text passages as the unit of
knowledge, which has high coverage at the cost of interpretability,
controllability, and efficiency. The opposite properties arise in other methods
which have instead relied …

arxiv language language models memory models open qa question answering