Pith. sign in

REVIEW 1 cited by

GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.05822 v1 pith:WMRPMVEH submitted 2021-06-10 cs.CL cs.LG

classification cs.CLcs.LG
keywords architecturelanguagemodelscomputationaldemonstratedenseefficientgrouped
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and large parameter count. In this work we demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. First, we add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. Secondly, we rely on grouped transformations to reduce the computational cost of dense feed-forward layers and convolutions, while preserving the expressivity of the model. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales. We further highlight its improved efficiency, both in terms of floating-point operations (FLOPs) and time-to-train.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation

    cs.CL 2025-02 conditional novelty 6.0 of 10

    PGB prunes BERT in a single pass by permuting weight matrices into block-diagonal groups of important weights and removing all other weights, matching or beating iterative baselines on GLUE and SQuAD.

Pith tools