Difference between revisions of "Ideas for Google Summer of Code/Distributed representations and Apertium"

From Apertium
Jump to navigation Jump to search
Line 9: Line 9:
 
* http://www.mt-archive.info/90/RANLP-1995-Wang.pdf
 
* http://www.mt-archive.info/90/RANLP-1995-Wang.pdf
 
* https://arxiv.org/pdf/1603.06318v4.pdf
 
* https://arxiv.org/pdf/1603.06318v4.pdf
  +
* Garcez, A. S. d., Broda, K., and Gabbay, D. M. (2012).Neural-symbolic learning systems:foundations and applications. Springer Science & Business Media
  +
   
 
[[Category:Ideas for Google Summer of Code|Distributed representations and Apertium]]
 
[[Category:Ideas for Google Summer of Code|Distributed representations and Apertium]]

Revision as of 23:49, 13 March 2020


Random ideas

  • Each module is a layer, and the layers are trained multitask, to copy the output of the module, and to create the final translation.

Bibliography