Apertium VS Lingvanex

This is very cool, looking forward to it! I've been doing the same thing with Spanish Wikipedia articles for a while, using a few lines of Bash + Regex. I was using Apertium for it. https://apertium.org/ It's definitely worse than most ML-based solutions, but it works reliably and fast; you can run it entirely offline. With Spanish translations, the main problem I was facing is lack of vocabulary, so I created - Source: Hacker News / 9 months ago

I used to keep track of the state of machine translation some years back. I think the way you measure the success of an automated translation is edit distance, i.e. How many manual edits you need to make to a translated text before you reach some acceptable state. I suppose it's somewhat subjective, but it is possible to construct a benchmark and allow for multiple correct results. The best resources I knew back... - Source: Hacker News / almost 2 years ago

Apertium is one of them. We make open-source rule-based machine translation systems, and our core tools are in C++. A few of our proposed ideas involve modifying those C++ tools with new features or improvements to existing features. Source: about 3 years ago

That being said some services that translate and respect privacy are out there. The one I know of off the top of my head is the one integrated into Vivaldi, Lingvanex. Source: about 1 year ago

We are partnered with lingvanex, all translation requests have IP/identifying information removed and such text is not retained after the request completes. Source: over 1 year ago

I loved when Vivaldi opted for translation services of Lingvanex "https://lingvanex.com/" and not of google but then you see they have DNS of google, chain of google enabled for login, phones back to google, dependant on google addon store, uses grid tabs and tab groups and the new share plate where only google apps show not the ones you use mostly to share things made by google for chrome, not for Vivaldi and... Source: over 1 year ago