How Well Does MTL Work?
-
@nargodian Unfortunately I am one of those people who can't easily learn new languages and absolutely hates waiting. How badly does a machine translation read?
-
@elijah-karger-bf3ubvf said in Bookworm Part 3 Vol. 5 Discussion!:
How badly does a machine translation read?
Hello,
As this would lead to us getting off topic for the current discussion, please feel free to open a new topic for community input.
Thank you
Edit: You can also refer to an older topic from awhile back, https://forums.j-novel.club/topic/2588/how-well-does-mtl-work?_=1617196482565 (although it is not directly related to Bookworm)
-
@elijah-karger-bf3ubvf Machine translation of typical documentation is "OK", but literature often uses uncommon words that the machines have trouble with.
I tried reading a machine translation of novels a while back. Without familiarity with the characters involved, it was very difficult to follow. It did not have consistency; a character could be referred to has "he" or "she" in alternate sentences. Any words that were in-universe (rather than straight Japanese) special terms could become pretty much anything.
-
@elijah-karger-bf3ubvf said in Bookworm Part 3 Vol. 5 Discussion!:
@nargodian Unfortunately I am one of those people who can't easily learn new languages and absolutely hates waiting. How badly does a machine translation read?
Machine translation for JP->EN is terrible, inconsistent, and frequently outright wrong. When I've tried being lazy and using machine translation, I frequently find myself going back to the JP to figure out what the machine translation is trying to say.
I don't even try for Bookworm, because Quof's translation is amazing and worth waiting for.
-
Just ended up moving posts around, and reviving this old thread.
-
@justaidan OK. Thank you all for educating the newbie. Let me see if I have everything. The WN is complete but only in Japanese, and the LN is incomplete. Assuming my language skills don't improve I need a translation. Machine translations don't sound like something anyone would willingly want to read but they are only option if I am truly unable to wait. Giving what I am feeling right now I think we all now know exactly how Ferdinand is going to get Myne to pass her language classes.
-
@elijah-karger-bf3ubvf Real quick so as not to derail the thread but I think there is also a sequel in the works and really don't read the machine translation, it's dire. You will struggle even to follow scenes and absolutely miss all the subtle stuff Bookworm is known for.
I can't stress how bad it is.
Quof's translation is excellent and on the threads you might see some of the background deliberations on the translation and discussions that happen between them and the original author to get the authors intent across. (Those might be one of my favourite behind the scenes stuff)
-
@elijah-karger-bf3ubvf You can try MTL yourself, if you're using Chrome as your browser and tell it to "Always translate Japanese". It can be real fun trying to figure out what books on Amazon.co.jp are about...
Here is a short example, translating a verse from Second Flight, the opening of Please! Twins!
Kanji:
きっと巡り合わせた 天使のほんの気紛れだよ
曲がり角で会ったみたいに ふっと始まってたRomaji:
Kitto meguriawaseta Tenshi no hon no kimagure da yo
Magarikado de atta mitai ni Futto hajimattetaMTL:
Surely Tour Ri If Align was heaven use of only a gas- powder Re'm
song rising angle in the meeting like the whiff was Tsu started had been waitingTranslation used in the anime subtitles:
It was definitely fated, it was just an angel's whim
It had begun so suddenly, as though we met on a street corner -
@someoldguy (Also Second Flight slaps)
-
@someoldguy said in How Well Does MTL Work?:
Kanji:
きっと巡り合わせた 天使のほんの気紛れだよ
曲がり角で会ったみたいに ふっと始まってたFor comparison, here's what DeepL gave me:
I'm sure it was just a whim of the angels that brought us together.
It all started so suddenly, like we'd just met at a corner.Which is to say, if you're going to use MTL, use DeepL, since it generally has better translations, and comes with a built-in editor where you can click on a translated word and get alternative translations, and if none of the alternatives fit, you can even type in your own suggestion, and DeepL will change its translation to fit your suggestion. You can either paste whole paragraphs, and let DeepL try to figure out the context (faster, but prone to severe errors), or you can paste a single sentence at a time, and do the job of decoding the context yourself (using DeepL's built-in editor).
And when DeepL fails, there's still Mirai Translate, which may or may not be able to make sense of things. It's still certainly better than Google Translate.
-
In that case are there any other humans working on translation that I should know about? I am kind of new on this scene so any other websites would be good to know about if that is OK. I doubt my language skills will improve much but I do love new books.
-
@waterdweller DeepL has been mentioned before; does it have browser integration available?
-
@elijah-karger-bf3ubvf Anything licensed by an overseas publisher has a actual human translators working on the books.
So anything from J-Novel Club, Yen Press, Seven Seas, Tentai, etc.
-
@someoldguy I'm afraid not. It does, however, have a Windows app that you can easily push text to through a keyboard shortcut (going via the clipboard).
Edit: it should have a MacOS app as well.
-
@waterdweller I saw that. Google has the advantage of being plugged into Chrome, so you just need to browse the page and (usually) get comic relief. A plug-in like the "reader view" would be very helpful.
I use auto-translate a lot on a forum that gets posts advertising apartment cleaning and dating services in various Russian cities, so I can tell who needs to be banned and for what reason. :)
Sometimes you can't copy/paste text very easily. Some pages even prevent you from highlighting text to get it into the clipboard, meaning you have to type things in. If I understood Japanese well enough to be able to type it in, I probably wouldn't need the translation.
-
Sometimes, Deep L works surprisingly well. But it's a lot of effort to learn the plot about a book without really "reading" it since you need to edit out the Japanese punctuation characters to avoid some bad Deep L glitches.
Someone more tech saavy could probably make a find / replace macro to replace these with their English equivalents.
。」』「『、…─
-
Something I'm really disappointed about Google translate is that they failed to build a community around it. A couple years ago, I was curious so signed up to be Google Translate Contributor.
https://translate.google.com/about/contribute/
You register the language you are good at, and then you go through a few different "tasks". One is that it will gives you bunch of short phrase or words one after another, and you enter its translation. Another task is that it will give you a word/phrase and it has multiple different translation of it, and then you pick the ones you think are good translation.
It is like a game and you go though bunch of them in a batch of a few dozen or so per session. You make more contribution of them and you can earn "batch" of different colors. But that's it! There is no list of contributors, no rankings of contributors, no place for contributors to discuss with each other. You are nobody.
It is a very lonely process and not fun at all, and didn't motivate me to keep on going.
-
This post is deleted! -
Since people posted here about DeepL, I gave it a try.
My impression is that DeepL gives a adequate translation about 85% of the time, makes bad inferences 10% of the time, and the remaining 5% it just makes stuff up that has nothing at all to do with the original text.
Here's an example of it making stuff up, from Town Building Game web novel.
JP:
常に余裕がある表情を心掛けて、笑顔を絶やさぬように気を張っていたので表情筋が固まってしまった。
がさっ、という物音と視線を感じたので足下に向けると、ディスティニーが俺を真似して自分の頬をモミモミしている。
……くっ、ちょっとかわいいと思ってしまった。
DeepL:
I was always trying to keep a relaxed expression on my face, and I was so careful to keep smiling that my facial muscles froze.
This is a great way to make sure you are getting the most out of your time with your family and friends.
I thought it was a little cute. ......
Me:
I'd been trying so hard to smile like I had everything under control that the muscles on my face had hardened.
I felt something at my feet, and when I looked down, Destiny was imitating me, giving himself a cheek massage.
I thought that was a little cute.I think my verdict is that, as with other MTL, use DeepL with caution and as a last resort. You'll need to know the source language anyway so you can fill in the gaps when the MTL makes mistakes, and if the MTL makes only small mistakes, you won't notice.
-
@rsog412 Odd, since this is what I get:
