2020

On Optimal Transformer Depth for Low-Resource Language Translation

van Biljon, Elan, Pretorius, Arnu, Kreutzer, Julia

Understand

Transformers have shown great promise as an approach to Neural Machine Translation (NMT) for low-resource languages.

  • However, at the same time, transformer models remain difficult to optimize and require careful tuning of hyper-parameters to be useful in this setting.
  • Many NMT toolkits come with a set of default hyper-parameters, which researchers and practitioners often adopt for the sake of convenience and avoiding tuning.
  • These configurations, however, have been optimized for large-scale machine translation data sets with several millions of parallel sentences for European languages like English and French.

Built on

  • Bleu: a method for automatic evaluation of machine translation

    Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu · 2002

    Earlier work this paper cites.

  • Statistical translation with scarce resources: a south african case study

    Kato Ronald and Etienne Barnard · 2007

    Earlier work this paper cites.

  • Processing parallel text corpora for three south african language pairs in the autshumato project

    J. Hendrik Groenewald and Liza du Plooy · 2010

    Earlier work this paper cites.

  • Dropout: A simple way to prevent neural networks from overfitting

    Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov · 2014

    Earlier work this paper cites.

  • Exploring unsupervised word segmentation for machine translation in the south african context

    Daniel R. van Niekerk · 2014

    Earlier work this paper cites.

  • Deep information propagation

    Original

    Samuel S Schoenholz, Justin Gilmer, Surya Ganguli, and Jascha Sohl-Dickstein · 2016

    Earlier work this paper cites.

Similar

  • Attention is all you need

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin · 2017

    Cited alongside, same era.

  • Towards neural machine translation for african languages

    Jade Z Abbott and Laura Martinus · 2018

    Cited alongside, same era.

  • Training tips for the transformer model

    Martin Popel and Ondřej Bojar · 2018

    Cited alongside, same era.

  • Critical initialisation for deep signal propagation in noisy rectifier neural networks, 2018

    Arnu Pretorius, Elan Van Biljon, Steve Kroon, and Herman Kamper · 2018

    Cited alongside, same era.

  • Reducing transformer depth on demand with structured dropout

    Original

    Angela Fan, Edouard Grave, and Armand Joulin · 2019

    Cited alongside, same era.

Then

  • A focus on neural machine translation for african languages

    Original

    Laura Martinus and Jade Z Abbott · 2019

    Later among the works it cites.

  • Auto-sizing the transformer network: Improving speed, efficiency, and performance for low-resource machine translation

    Kenton Murray, Jeffery Kinnison, Toan Q Nguyen, Walter Scheirer, and David Chiang · 2019

    Later among the works it cites.

  • Facebook fair’s wmt19 news translation task submission, 2019

    Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, and Sergey Edunov · 2019

    Later among the works it cites.

  • Transformers without tears: Improving the normalization of self-attention

    Toan Q Nguyen and Julian Salazar · 2019

    Later among the works it cites.

  • Rezero is all you need: Fast convergence at large depth

    Original

    Thomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao, Garrison W. Cottrell, and Julian McAuley · 2020

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…