Ideas for Google Summer of Code/Distributed representations and Apertium
Jump to navigation
Jump to search
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
- http://www.mt-archive.info/90/RANLP-1995-Wang.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
