10 décembre 2020
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.37011/lingaeg.28.07
http://creativecommons.org/licenses/by-nc-nd/ , info:eu-repo/semantics/OpenAccess
Serge Rosmorduc, « Automated Transliteration of Late Egyptian Using Neural Networks: An Experiment in “Deep Learning” », HAL-SHS : histoire, ID : 10.37011/lingaeg.28.07
We apply deep Learning techniques to the task of automated transliteration of Late egyptian. after a brief presentation of the technology used, we examine the result to highlight the capabi- lities of the system, which is able to deal with a wide range of problems, including grammatical and phraseological ones. We then proceed to extract signs values from what the system has automatically learnt.