Building a language translator from scratch with deep learning
21–30 of 38 posts
Re: Building a language translator from scratch with deep learning
#22Machine translation has made some pretty impressive progress over the last decade. Unfortunately no methods will ever cover the very last mile as languages don't have perfect 1 to 1 mappings. Though it is amusing watching the machines try.
If we ever do solve the last mile, it would probably be one of the less interesting consequences, as it would probably imply we've built an algorithm capable of learning and thinking to a similar degree of a human. To that, though, I'm definitely not holding my breath :)
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing.
Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's say we are excluding the last mile for arguments sake). That assumption ignores an important fact that sometimes translation is a team effort where certain words, phrases or concepts are debated among multiple translators to reach a consensus. It's not always done by a single intelligence.
Some people might argue that's because people have far more limited capacity to consider all the examples in the corpus whereas a machine can consider all of lightning fast and thus can arrive at the right answer.
A perfect edge case that illustrates why that doesn't matter and where multiple human intelligences will often grapple with how something should be translated would be what name to give to a movie you are translating to an international audience. The same movie often has quite different names depending on which language it gets translated into. There isn't actually a correct answer there is just answers that are deemed 'good enough'.
Re: Building a language translator from scratch with deep learning
#23Earlier quoted context omitted.
If we ever do solve the last mile, it would probably be one of the less interesting consequences, as it would probably imply we've built an algorithm capable of learning and thinking to a similar degree of a human. To that, though, I'm definitely not holding my breath :)
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing. Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's…
I suppose we should just give up the whole enterprise and not bother trying at all, or what are you saying? Maybe we can't ever solve the "last mile", so what?
Re: Building a language translator from scratch with deep learning
#24Earlier quoted context omitted.
If we ever do solve the last mile, it would probably be one of the less interesting consequences, as it would probably imply we've built an algorithm capable of learning and thinking to a similar degree of a human. To that, though, I'm definitely not holding my breath :)
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing. Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's…
You know, though, machine translators have long been able to make subjective choices in translations. We deem them correct because a human can verify that the translation carries roughly the same intent, meaning, tone, etc. Not because it matches exactly what a human says.
Secondly, you are conflating concepts in my opinion. Localizing a movie may involve translators translating lines, but it also involves the creative work of localizing the title and other things, as you mentioned. A machine translator by today's definition translates a string of text in one language to a string of text in another. We needn't consider every type of work a human translator might do; it would be quite enough of a difference to close the gap on translating strings straightforwardly.
Re: Building a language translator from scratch with deep learning
#25This is very cool. One thing I wonder about though is whether small companies will be able to compete with large ones like Google in ML in the future. One reason Google's translator is better is because they have way more data. In the past they digitized tons of books so they have an excellent dataset that has been translated by professional, human translators. This data collection is effectively cross-subsidized by…
Deepl is already MUCH better than Google translate: https://www.deepl.com/translator
Re: Building a language translator from scratch with deep learning
#26Earlier quoted context omitted.
If we ever do solve the last mile, it would probably be one of the less interesting consequences, as it would probably imply we've built an algorithm capable of learning and thinking to a similar degree of a human. To that, though, I'm definitely not holding my breath :)
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing. Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's…
> The last mile isn't solvable.
So true. Often the last mile isn't solvable even for highly trained humans: it's not like it's hard, it just impossible.
Translators have to take alternative ways to convey the meaning. Making choices, and often losing some parts completely.
Machines have no chances.
Re: Building a language translator from scratch with deep learning
#27Machine translation has made some pretty impressive progress over the last decade. Unfortunately no methods will ever cover the very last mile as languages don't have perfect 1 to 1 mappings. Though it is amusing watching the machines try.
Though it is amusing watching the machines try.
I remember watching a program back in high school subtitling music videos with their lyrics machine translated from English to Hungarian. The absurdity was indeed hilarious for a brief period.
Re: Building a language translator from scratch with deep learning
#28Earlier quoted context omitted.
If we ever do solve the last mile, it would probably be one of the less interesting consequences, as it would probably imply we've built an algorithm capable of learning and thinking to a similar degree of a human. To that, though, I'm definitely not holding my breath :)
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing. Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's…
> The last mile isn't solvable.
This does not really apply to your movie name example, but in a text machines could try to escape to a meta-level, like humans sometimes do: "There is an old gaelic saying, which, roughly translated, goes something like this..."
Re: Building a language translator from scratch with deep learning
#29This is very cool. One thing I wonder about though is whether small companies will be able to compete with large ones like Google in ML in the future. One reason Google's translator is better is because they have way more data. In the past they digitized tons of books so they have an excellent dataset that has been translated by professional, human translators. This data collection is effectively cross-subsidized by…
DeepL had a lot of good press when it came out last year. Some saying it was better than Google. https://www.deepl.com/en/translator
When someone recommended DeepL to me I almost didn't take it seriously expecting mediocre translations that aren't bad, but hardly usable without heavy editing. However after trying it I'm very impressed with its results and in those cases where you have a better translation in mind the interface offers an easy way to suggest and replace expressions. It's impressive.
Re: Building a language translator from scratch with deep learning
#30Earlier quoted context omitted.
The last mile isn't solvable. Some languages contain concepts, set phrases, vocabulary and pop-culture references entirely unique to that language. There isn't a translation in every single case. Machines however will always try to come up with one and the results are amusing. Also people make the assumption that as soon as we make strong AI comparable to a human we will be to translate anything and everything (let's…
> The last mile isn't solvable. This does not really apply to your movie name example, but in a text machines could try to escape to a meta-level, like humans sometimes do: "There is an old gaelic saying, which, roughly translated, goes something like this..."
That is the only end game I would consider to be a full implementation of machine translation on par with human capabilities.
In cases where there is no direct equivalent or even an appropriate localization we usually resort to giving a long form explanation. If the machines can do that, they've won.
I can't see the current techniques getting us that far. It's going to require some new, creative thinking to really push the envelope.