That is… absolutely true, and yet “I missed my flight” probably should be in the list of canned phrases that can just be looked up in a dictionary, along with “Where is the bathroom” and ”Check, please”.

Japanese and Korean languages are pretty hard to translate.

In Korean, 나좀 봐주라 literally translates into "Look at me", but in most cases, it means, "cut me some slack".

Google translate gets this wrong.

If you Google translate "cut me some slack" into either Korean or Japanese, it also fails.

But if you translate Japanese phrase "もう勘弁してくれよぉ" into English, it is translated into "Please forgive me already", but in reality, it's more like, "Cut me some slack! Or give me a break!"

Translation is hard.

Even French and German are hard, comparing deeply.org to Google translator shows how awful the latter is.

Same with Russian (Yandex does an OK job).

But https://www.deepl.com is pretty amazing in my experience for the languages it's available for.

This become even more awful when the target language is not English because English is used as a pivot language: there is now two rounds of errors. I’ve heard from a researcher specialized in the AT field that a rule based Japanese to French system exists and is quite good but I’ve never seen the system itself.

I wonder, would another language serve better as a "pivot", all else equal (like, let's ignore corpus size)? English is both a wonderfully expressive but also frustrating language because of its vocabulary's flexibility, ambiguity, and adaptability.

french used to be the language in which international laws and treaties were written because it’s supposed to be one of the most precise.

later, german was the language of choice of philosopher because of its rigourous structure and the ability to make new words just by combining them.

now it’s english, because it’s the easier to learn.

but also the real reason was the economical power of its time impose its language. The reason english was chosen probably is only because the software developers were english.

I think slavic language would be the best though, because every single word takes a different variation if they’re about a man or woman, etc. So there’s probably the least amount of ambiguity.

But probably an invented intermediate language would be the best. Except the google style translators don’t try to infer any meaning, which makes it hard to reason about.

Funny English sounds like PHP programming language when it's used broadly, relatively easy to understand but sometimes the rules are too loose and some other languages are more strict but not everyone likes the strictness.

A paper or webpage I read long ago about Bing Translate internals mentionned to use of an intermediate language that was artificial.

Esperanto?

why have one pivot at all? why can't french be the pivot between spanish and english?

if we must have one and you believe in euroversals, then german and/or french might be better than english…

Resources availability. English/X or X/English pairs probably exist for a lot of X and may be well endowed. But for any other X/Y pairs resources may not exist at all or be too small to use. That being said it is still interesting to develop this kind of ressources (for example dictionaries) because they can be used for other NLP tasks.

Google translate seems to get the correct phrase so at least there's hope.

When you click on the translation in google it gives you the option of 'improve answer' in the drop down.

There's a huge amount of fixed phrases because google's translate didn't actually get it right unfortunately.

I expect that future work which provides concepts in the external world to models will eventually do better. Translation by context rather than content has limits.

Reminds me of this article by Douglas Hofstadter: https://www.theatlantic.com/technology/archive/2018/01/the-s...