Log In Sign Up

Tricks for Training Sparse Translation Models

by   Dheeru Dua, et al.

Multi-task learning with an unbalanced data distribution skews model learning towards high resource tasks, especially when model capacity is fixed and fully shared across all tasks. Sparse scaling architectures, such as BASELayers, provide flexible mechanisms for different tasks to have a variable number of parameters, which can be useful to counterbalance skewed data distributions. We find that that sparse architectures for multilingual machine translation can perform poorly out of the box, and propose two straightforward techniques to mitigate this - a temperature heating mechanism and dense pre-training. Overall, these methods improve performance on two multilingual translation benchmarks compared to standard BASELayers and Dense scaling baselines, and in combination, more than 2x model convergence speed.


page 1

page 2

page 3

page 4


nmT5 – Is parallel data still relevant for pre-training massively multilingual language models?

Recently, mT5 - a massively multilingual version of T5 - leveraged a uni...

Adaptive Sparse Transformer for Multilingual Translation

Multilingual machine translation has attracted much attention recently d...

Multi-task Learning for Multilingual Neural Machine Translation

While monolingual data has been shown to be useful in improving bilingua...

Top-KAST: Top-K Always Sparse Training

Sparse neural networks are becoming increasingly important as the field ...

Facebook AI WMT21 News Translation Task Submission

We describe Facebook's multilingual model submission to the WMT2021 shar...

Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models

Massively multilingual models subsuming tens or even hundreds of languag...

Adaptive Scheduling for Multi-Task Learning

To train neural machine translation models simultaneously on multiple ta...