Augmenting Transformers with KNN-Based Composite Memory

By Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes. 2019

Subfields: Retrieval-Augmented Generation, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Retrieval-Augmented Generation

1. Sebastian Riedel
2. Wen-tau Yih
3. Fabio Petroni
4. Patrick Lewis
5. Michael Lewis
6. Douwe Kiela
7. Akari Asai
8. Vladimir Karpukhin

In Model Architectures

1. Sebastian Riedel
2. Tim Rocktaschel
3. Wen-tau Yih
4. Patrick Lewis
5. Douwe Kiela
6. Ethan Perez
7. Michael Lewis
8. Naman Goyal

Citations in the corpus

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020, background): “Such tasks include open-domain question answering [5, 25], fact checking [50], fact completion [42], long-form question answering [12], Wikipedia article generation [32], dialogue [36, 59, 9, 13], translation [16], and language modeling [17, 23].”