Big Bird: Transformers for Longer Sequences

by   Manzil Zaheer, et al.

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having O(1) global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.



page 1

page 2

page 3

page 4


ETC: Encoding Long and Structured Data in Transformers

Transformer-based models have pushed the state of the art in many natura...

Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences

Transformers-based models, such as BERT, have dramatically improved the ...

Flowformer: Linearizing Transformers with Conservation Flows

Transformers based on the attention mechanism have achieved impressive s...

Dynamic N:M Fine-grained Structured Sparse Attention Mechanism

Transformers are becoming the mainstream solutions for various tasks lik...

Time-based Sequence Model for Personalization and Recommendation Systems

In this paper we develop a novel recommendation model that explicitly in...

On the Computational Power of Transformers and Its Implications in Sequence Modeling

Transformers are being used extensively across several sequence modeling...

On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers

How much information do NLP tasks really need from a transformer's atten...

Code Repositories



view repo


dd2412 project at KTH

view repo


Develop analysis model from bigbird model

view repo


Final Project for CS523

view repo


An implementation of the minGPT architecture using BigBird masking.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.