Hacker News Reader

Comment by kuschku | Hacker News Reader

60% better than Google translate still is at best elementary school level fluency in a language. It’s a needed improvement, but still far from good.

It’s crazy how bad Google translate is, try it with any German text, and you’ll get 90% ununderstandable garbage out.

EDIT: Seriously, downvotes for this?

Try this: https://translate.google.com/translate?sl=auto&tl=en&js=y&pr...

What’s " If you look at Ursula von der Leyen and Jean-Yves Le Drian before the meeting of defense ministers in Bratislava, one might think that Berlin and Paris would never prefer liked." supposed to mean?

Or "Individual states can not prevent the European Council may decide by a qualified majority, the SSZ."

View on HN

I think you're getting downvoted because you picked one of the hardest language pairs there is for machine translation. German grammar is really hard to parse, e.g. verbs being split with one part at the beginning and the other at the end of the sentence. Generally, figuring out which part of the sentence refers to which other part is quite hard.

Google Translate works a lot better with many other language pairs, so people might be downvoting because your opinion sounds exaggerated and doesn't line up with their own experience. It's also quite dismissive of the submission, which is never nice. The guidelines ask us to "avoid gratuitous negativity". I often find your comments to be quite negative, often unnecessarily so.

It seems like I forgot the actual point of my argument – "It’s a needed improvement, but still far from good".

> I often find your comments to be quite negative, often unnecessarily so.

Well, if it’s a relief, I’m equally negative about stuff I create myself.

Translations from French to English seem to be a lot better. Why is that?

The French/English language pair was the problem machine translation research started with and has seen the most work. There are also greater similarities than most language pairs between those two due to the Norman conquest in 1066.

I accept your first point, but I disagree with your second - 1066 and all that notwithstanding, English is still very much a Germanic language, and grammatically very different from French.

You're right; I was arguing that French and English are more highly correlated than a pair of languages chosen uniformly at random and therefore easier for MT, but I could have made that more clear. I think the difference in accuracy between English <--> French and English <--> German does largely come down to historical academic preferences and data availability, as opposed to linguistic reasons. English <--> French vs. English <--> Mandarin (for example) is a different story.

There is clearly a lot of room for improvement. This is what I got translating from Russian:

    I personally think that this program is not so bad works. Sometimes she makes mistakes, but this is fairly rare.

The grammar is bad, but you can understand the meaning here.

Some people don't realize it, but perfect translation is actually an "AI-complete" task:

For example, "program" is a "she" in Russian and "it" in English. To translate such pronouns correctly (among other challenges), one needs to figure out what they refer to, and for that one needs common sense.

You mean the uncommon sense and much better trained, more complex network.

(By uncommon I mean it is rare, and also I mean that it should find the rare instances and learn much from them.)

That actually seems pretty impressive for machine translation. Also, you have to look at the rate of improvement in machine translation -- not so long ago, it was much, much worse. And Google is leading the pack here, and due to the rate of improvement so far (and this article!) we expect it to continue to improve, and it is exciting and positive to see this improvement, and surprised that we're being told how the improvement is performed!

What do you propose as an alternative? Human translation of everything and no research in machine translation?

I don't think that matters will improve unless machine translation systems are built which understand the meaning of the words in the text which they are translating, and know the grammar of the source and target texts, just like people do.

Look at this graph: https://1.bp.blogspot.com/-jOLa-LdidQU/V-qV2oJn1aI/AAAAAAAAB...

On French > English and English > Spanish it's almost indistinguishable from human translations. On the rest it still gets greater than half the distance between the previous best method and human quality translations. This is a massive step forward.

Yes, I’m saying, it’s an awesome improvement, but considering where we’re today, the result will still be far from human.

It’s definitely needed, but not nearly enough.

Nematus (https://github.com/rsennrich/nematus), which takes a similar approach to this paper, gives:

"If you look at Ursula von der Leyen and Jean-Yves Le Drian before the meeting of defence ministers in Bratislava, you could never have liked to have liked Berlin and Paris."

which is still doesn't convey the true meaning of something like: "you might think Berlin and Paris had never liked each other more."

However, the second sentence comes out as:

"Individual states cannot prevent this: The European Council can adopt the SSC by a qualified majority."

which is significantly better than Google translate.

That’s actually an awesome improvement already.

Maybe in a decade or so we can actually use translation software then to read newspaper articles in foreign languages.

Thanks for giving a context.

This is not (at the time of publication) the production backend for Google Translate:

"In addition to testing on publicly available corpora, we also test GNMT on Google’s translation production corpora, which are two to three decimal orders of magnitudes bigger than the WMT corpora for a given language pair. We compare the accuracy of our model against human accuracy and the best Phrase-Based Machine Translation (PBMT) production system for Google Translate."

Blog post says it launched for Chinese/English.

ah, interesting, I've only read the linked paper (and this news hasn't made it to our internal "cool stuff we've launched recently" newsletter).

Still, OP was complaining about the quality of German->English, which is still using PBMT, so...

No, I was saying "German->English with PBMT is so bad, even +60% better is still not nearly good enough".

It’s crazy how bad Google translate is, try it with any German text, and you’ll get 90% understandable garbage out.

But that could have more to do with how crazy the German language is ;)

Downvoter(s): German sentences -are- intrinsically more complex ("crazy") on average, than English sentences. This is a known, and fairly basic point. So it's not surprising that they should be correspondingly difficult for translation algorithms to "chew on", and provide 1-1 mappings for.

The papers this NMT only applies to Chinese-English translations.

Reply on news.ycombinator.com