Retrieval augmentation is a powerful but expensive method to make langua...
Memory-augmentation is a powerful approach for efficiently incorporating...
Multi-query attention (MQA), which only uses a single key-value head,
dr...
Many natural language processing tasks benefit from long inputs, but
pro...
Retrieval-augmented language models such as Fusion-in-Decoder are powerf...
Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model...
A common recent approach to semantic parsing augments sequence-to-sequen...
In this position paper, we propose a new approach to generating a type o...
Retrieval augmented language models have recently become the standard fo...
Natural language understanding tasks such as open-domain question answer...
Training a reinforcement learning agent to carry out natural language
in...
Knowledge-intensive tasks such as question answering often require
assim...
Neural symbolic processing aims to combine the generalization of logical...
Motivated by recent evidence pointing out the fragility of high-performi...