Difference between revisions of "Apertium-neural"

From Apertium
Jump to navigation Jump to search
(Created page with "Apertium was originally developed to offer a free/open-source framework for creating RBMT systems. It was modelled on existing systems, but targetted at related languages, try...")
 
m (Francis Tyers moved page Neural machine translation to Apertium-neural)
(No difference)

Revision as of 21:19, 21 June 2020

Apertium was originally developed to offer a free/open-source framework for creating RBMT systems. It was modelled on existing systems, but targetted at related languages, trying to do one thing well.

What might an Apertium NMT system for lesser-resourced and marginalised languages look like?

Thoughts:

  • Trains without GPU or large compute
  • Optimised for small corpora (under 100k parallel sentences)
  • Includes linguistic tricks
  • C++, autotools
  • Works with existing tools (formatters, APY etc.)

Pipeline(?):

apertium-destxt | apertium-preprocess | apertium-encode | apertium-decode | apertium-retxt