pith. machine review for the scientific record.
sign in

arxiv: 1606.09274 · v1 · pith:SURNGODMnew · submitted 2016-06-29 · 💻 cs.AI · cs.CL· cs.NE

Compression of Neural Machine Translation Models via Pruning

classification 💻 cs.AI cs.CLcs.NE
keywords pruningtranslationarchitecturecompressionmachinemodelmodelsneural
0
0 comments X
read the original abstract

Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture. We demonstrate the efficacy of weight pruning as a compression technique for a state-of-the-art NMT system. We show that an NMT model with over 200 million parameters can be pruned by 40% with very little performance loss as measured on the WMT'14 English-German translation task. This sheds light on the distribution of redundancy in the NMT architecture. Our main result is that with retraining, we can recover and even surpass the original performance with an 80%-pruned model.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination

    cs.LG 2025-10 unverdicted novelty 5.0

    TALE selectively prunes task-detrimental layers in LLMs at inference time to match or exceed baseline performance with lower computational cost across multiple models and tasks.