Which are based on LLMs or other statistical language models. It is kind of the thing that language models are good at.
See DeepL for example: en.wikipedia.org/wiki/DeepL_Translator
The service uses a proprietary algorithm with convolutional neural networks (CNNs)[3] that have been trained with the Linguee database.[4][5]
According to the developers, the service uses a newer improved architecture of neural networks, which results in a more natural sound of translations than by competing services.
The translation is said to be generated using a supercomputer that reaches 5.1 petaflops and is operated in Iceland with hydropower.[6][7]
In general, CNNs are slightly more suitable for long coherent word sequences, but they have so far not been used by the competition because of their weaknesses compared to recurrent neural networks.
The weaknesses of DeepL are compensated for by supplemental techniques, some of which are publicly known.
ArchmageAzor@lemmy.world 7 months ago
Honestly, translations are one of the few things LLMs are good for. It can catch things like idioms or other things a machine translator may mistranslate. Though tbf, the main appeal is still live translation.
fossilesque@mander.xyz 7 months ago
I want my Babbelfish.