Hacker News new | past | comments | ask | show | jobs | submit login

Both are hard and are open problems.



Sure, but very different. Mapping requires real-world operations, such as driving cars and taking pictures around the entire world, and doing it again and again.

This is far more cost-intensive, both in upfront as in maintenance, than the translation problem.

Software is easy. The real world is hard.


Which is exactly the point. Translation is a real-world problem. You need to actively go into the real world, find problem cases, make your translation software translate it, make your own translation, compare the translations, teach your software to translate it correctly, and hope that your approach is good enough.

The real-world constraint of translation software is building a sizeable quality corpus of real-world text with real-world living human translators. We're lucky that the EU employs literally thousands of translators to publish identical texts across languages (for free!!), which has helped make European languages pretty much a solved problem in machine translation. But anything non-european is still hopelessly incomprehensible, simply because we don't have enough real-world data.


Since they are using this strategy, translation of idioms is terrible. I have switched translate.


To what?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: