Natural language processing with neural networks
Outlook
The example shown here is the subject of current research in the field of language technology. Scientists are currently still investigating questions such as: Which weighing of the individual factors, such as translation quality and synchronization quality, optimizes the overall quality? At which point exactly do people even notice that the lip-sync is no longer perfect?
It is also important to remember that world languages vary considerably. Consequently, this problem is so complex that a single model cannot do justice to it. As a result, it is essential to train separate models for the different pairs of languages to be translated.
Infos
- "Computing Machinery and Intelligence" by A.M. Turing, Mind, volume LIX, October 1950, pp. 443-460, https://academic.oup.com/mind/article/LIX/236/433/986238
- Karpathy (2015); http://karpathy.github.io/2015/05/21/rnn-effectiveness/
« Previous 1 2
Buy this article as PDF
(incl. VAT)