activity
20192026
most citedGenerate-and-Retrieve: use your predictions to improve retrieval for semantic parsing

8 citations · 13 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2023

MEMORY-VQ: Compression for Tractable Internet-Scale Memory

Yury Zemlyanskiy, Michiel de Jong, Luke Vilnis +4

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representati…

cs.CL2023

GLIMMER: generalized late-interaction memory reranker

Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald +3

Memory-augmentation is a powerful approach for efficiently incorporating external information into language models, but leads to reduced performance relative to retrieving text. Re…

cs.CL2023

GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Joshua Ainslie, James Lee-Thorp, Michiel de Jong +3

Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference. However, MQA can lead to quality degradation, and moreover it may not…

cs.CL2023

CoLT5: Faster Long-Range Transformers with Conditional Computation

Joshua Ainslie, Tao Lei, Michiel de Jong +9

Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but…

cs.CL20228 cited

Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing

Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie +5

A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this…

cs.CL2021

ReadTwice: Reading Very Large Documents with Memories

Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong +3

Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose…