SOTAVerified

Compressive Transformers for Long-Range Sequence Modelling

2019-11-13ICLR 2020Code Available1· sign in to hype

Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Timothy P. Lillicrap

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We present the Compressive Transformer, an attentive sequence model which compresses past memories for long-range sequence learning. We find the Compressive Transformer obtains state-of-the-art language modelling results in the WikiText-103 and Enwik8 benchmarks, achieving 17.1 ppl and 0.97 bpc respectively. We also find it can model high-frequency speech effectively and can be used as a memory mechanism for RL, demonstrated on an object matching task. To promote the domain of long-range sequence learning, we propose a new open-vocabulary language modelling benchmark derived from books, PG-19.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
enwik8Compressive Transformer (24 layers)Bit per Character (BPC)0.97Unverified
Hutter PrizeCompressive TransformerBit per Character (BPC)0.97Unverified
WikiText-103Compressive Transformer (18L, M=1024)Test perplexity17.1Unverified

Reproductions