HiddenPineapple
Eugen RochkoMachine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.
I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.
Vile Lasagna@Gargron Back in my pretentious high schooler days I read Dante's Comedy and, don't know where from, the version I found was one that was like... fully translated as poetry, like in the Italian* original, going as far as trying to replicate the rhyme structure
No computer's ever going to pull off anything even remotely that mad
maco@VileLasagna @Gargron oh that’s probably John Ciardi’s translation
K M Lawrence@maco @VileLasagna @Gargron oh, I would have assumed the Dorothy L Sayers translation. Good lord, are there two rhyming translations into English?
arrbee@kludgekml @maco @VileLasagna @Gargron
I think are quite a few such translations ( even Clive James had a go ! ), but afaik none that attempt to replicate the same rhyming scheme Dante used - which may well be impossible in English.
I think are quite a few such translations ( even Clive James had a go ! ), but afaik none that attempt to replicate the same rhyming scheme Dante used - which may well be impossible in English.
Hugo Mills@kludgekml @maco @VileLasagna @Gargron I've got one by the Rev Francis Carey, which (I think) attempts to follow the rhyming. It's been a while since I tried reading that one, though.
(I primarily bought the volume because it's got loads of full-page plates of Doré illustrations).
@VileLasagna @Gargron I've read a few translations (into English) of the Divine Comedy, and the one that attempted to replicate the terza rima was 19th century, and (to me) almost unreadably difficult to deal with. Victorian translators weren't all that good, by modern standards, in my (admittedly fairly limited) experience.
Charlie Stross@Gargron I'm willing to guess that machine translation of prose may serve two uses: firstly, as an assist for human translators (by preparing a very rough first cut, which they then have to refine), and secondly, as an assist for human editors in figuring out which foreign-language-works to pay a human translator (with or without AI assistance) to work on (translation costs money: knowing where to spend it is important). But those are assistive roles, not human-replacing ones.
Ciarán Ferrie@cstross @Gargron I have a friend who worked for years as a translator (English to French) but in recent years he found that he was no longer being asked to translate but to "post-edit" machine translations. It was taking him just as long, paying him less, and destroying his soul.
He now works as a tour guide.
C++ Wage Slave
fedithom
Gerardo LisboaYour friend should have asked for more money, as that was clearly to clean up someone's mess.
As you do when asked to clean stupid code.
AnneH
Dena@cstross @Gargron
Machine translations are more of a hindrance than a help, for translators. If you don't know both languages well, having an automated dictionary lookup could possibly be useful - but if you're a translator, and especially a translator of fiction, having a nuanceless draft will only take more time to figure out. And it will be irritating time, because reading mistranslations is a pain. Editing one's own drafts is hard enough!
As to B: Editors rely on readers, reviews /...
HighlandLawyer@Shunra @cstross @Gargron
My go-to example is the Esperanto translation of Alice Through The Looking Glass published by Evertype, which has 5 different translations of "Jabberwocky", each of which is absolutely "correct" and each of which is totally different from each other. Even the names of the poem differ.
In each case one can see the decisions the translator made balancing meter, rhyme, meaning, implications & nuance of the text, based on what it meant to them; how can a computer do that?
My go-to example is the Esperanto translation of Alice Through The Looking Glass published by Evertype, which has 5 different translations of "Jabberwocky", each of which is absolutely "correct" and each of which is totally different from each other. Even the names of the poem differ.
In each case one can see the decisions the translator made balancing meter, rhyme, meaning, implications & nuance of the text, based on what it meant to them; how can a computer do that?
bri
Teemu Kalvas
Pare@cstross @Gargron My (very not translator) impression is that human translators who have worked from rough machine translations, say that it’s harder than just translating the text.
Also, today I was in a work info session, where the talks were translated by some MS PoS thing, from Finnish to English. The results were horrendous, if hilarious. It might get better but I don’t really know why. Good simultaneous interpretation is kind of a human-level problem, really. Context matters!
Curioso 🍉 🇺🇦 (jgg)I feel pretty dumb telling this to the master, but translating a literary work is much more than changing one word for another. Even it you keep all the meaning, it gets weird and doesn't flow; each language has its own rhythm and cadence. A good translator frequently has to completely rewrite a paragraph to keep the sense, the emotions and the flow of the story. Even worse, he needs to make it faithful to the original, which having intermediate versions can make harder.
I'm not a professional translator, but I have tried to translate some public domain stories, and found that automatic translation is a hindrance. I had to rewrite nearly all, looking always to the original version. It was too easy to drift far from it and get the text and the author absolutely distorted.
It is a work of art and love, not something a machine can do at all. Not even a part of it.
Gourd
Hannah SteenbockI sometimes translate text (bilingual German-English). And I have edited a machine-translated book, and let me tell you it does NOT save time.
I basically had to go back and rewrite almost every sentence. It was so bad the publisher actually put me on the cover as translator.
DeepL is good for short non-fiction stuff, and even that needs to be polished if you want to use it for anything serious.
Do not rely on anything AI. Never.
sotolfAs someone that has done some translation work, a machine translation template has ended up being more of a hinderance to me than help, it makes my brain lock into a pattern of the choices made by it, and it ends up being a way more clunky and weird feeling text than something I translated from the start.
xrvs@Gargron Crunchyroll also experiments with machine translated subtitles for Japanese anime, and the community (anglophone or not) is not happy with it.
geolaw
spooky Ske-Lil-ton 🦇@geolaw @Tacas @Gargron their subtitles for the English dub are also terrible in a way that can only be machine generated without any oversight
Besides "misheard" words, missing punctuation and names changing their spelling it is also never clear who says what or when a different person starts talking
I hate it so much (and I'm at least able to notice when they are wrong since I'm not deaf and can understand the audio in most cases. It must be worse for others)
Besides "misheard" words, missing punctuation and names changing their spelling it is also never clear who says what or when a different person starts talking
I hate it so much (and I'm at least able to notice when they are wrong since I'm not deaf and can understand the audio in most cases. It must be worse for others)
Asta 📚🧶🪡
Pax Ahimsa Gethen@Gargron - I think the most recent translated book series I read was Liu Cixin's Remembrance of Earth's Past trilogy,* translated into English by Ken Liu and Joel Martinsen. I don't know a word of Chinese, but I can't imagine machine translation doing these great works any justice.
* Later adapted into the Netflix series 3 Body Problem
tschenkel* Later TERRIBLY BADLY adapted into the Netflix series 3 Body PROBLEM
If you like the books, watch the Chinese original. Unfortunately it's only the first book so far.
Stephen Dioxide 
@Gargron As someone who translates into English, I appreciate you saying this.
It's true there's a lot of very good literature in English, but I'm pretty convinced that the majority of anglophones don't know what they're missing by not reading translated books.
James Gilbert@Gargron I've just bought an English translation of Mikhail Bulgakov's The Master and Margarita. I wondered which was the best translation, and found a website with multiple translations of the opening page. It was really interesting how different they were. The one by Diana Burgin's and Katherine Tiernan O'Connor was the clear winner for me.
gorfeld 
Michael Cook@Gargron Native speaker: I think you’re right. Though I have seen warnings recently about “new translation” editions on Amazon that are just LLM trash.
Claudio C@Gargron @mastodon.social I absolutely agree.
On the other hand, although I'm a native spanish speaker, I've read a couple of books in english.
I think that US pleople don't even consider reading in any language but english.
On the other hand, although I'm a native spanish speaker, I've read a couple of books in english.
I think that US pleople don't even consider reading in any language but english.
Wilfried Klaebe@cktodon I've seen a work of Terry Pratchett "translated" (by a human though) from British English to US English. To even have the idea this could be useful enrages me.
datarama@Gargron I've read translations of Haruki Murakami's novels in English and my native Danish - and I've found the latter *far* better. I can't judge the fidelity to the originals because I don't speak Japanese, but at least my reading experience with the Danish translations were a lot better - and I've probably read at least ten times as much English in my life as Danish.
I learned a while ago that the Danish translator of most (possibly all) Murakami's books has lived in Japan, knows Murakami personally, and talks to him about her translation work. And, well, the level of care put into those translations really shows.
The German translations of Terry Pratchett's Discworld novels by Andreas Brandhorst are quite good - but 50% of the jokes are intranslatable puns, and of the rest, he broke a lot because he didn't understand them.
I had to translate some joke around Hex back to understand it. Afterwards, I only read them like Terry had written them.
@wonka @Gargron I generally prefer to read things in their original language if I can. I've never read the Danish translations of Discworld (and I suspect the running gag about the Librarian's trigger word would fall completely flat in both Danish and German, for the same reason!).
But a couple of years ago I started reading Danish translations of literature in languages I don't speak (French, Arabic, Japanese, etc.) - I'd usually defaulted to English for no good reason. The Danish ones are sometimes better, sometimes worse - but in the case of Murakami it really wasn't even close.
Mayank@Gargron 💯 languages are usually not 1:1, and translation is impossible to automate without butchering the original meaning.
bad translation really sticks out when you understand both languages. even if it's serviceable enough to get the core meaning across, it might fail to capture the tone, the cultural references, and the full weight.
i have a lot of respect for people who create good subtitles that try to preserve the original intent, even when it sometimes feels impossible.
Tubemeister@Gargron Yes. My wife for years shunned Pratchett completely because she read a Dutch translation in the 90s.
Damien (TIG BUSINESS)@Tubemeister @Gargron puns are extra hard.
@aeduna @Gargron Oh yes. Translating the story is one thing, but especially with Pratchett it’s only half the story.
Puns are horrible to translate, you either just skip them because they just don’t work, or you go to extremes to wring some kind of joke out of them.
There isn’t necessarily a right approach here. This particular Pratchett translation apparently skipped a lot, but I also remember a HHGTTG translation that took the “a joke at *any* cost” path and um.
@Tubemeister @Gargron Asterisk provides an alternative where you replace it with another pun, but that's beyond translation :)
I don't have a reference, but I remember reading that later translations to dutch specifically were much better - it wasn't a quick and dirty word for word, someone was employed to put some real work into trying to keep the sense of the joke there.
Erik Uden 🍑@Gargron thank you. When writing the German subtitles for No Other Land I had to basically do it all by hand because the context window was so narrow it got everything wrong that could be lost in translation.
@Gargron machine learning can utilize all written text to help understand language and make translations better?? So basically my plagiarism machine is justified. Got em.
GunChleoc
Michel Decurtins@ErikUden @Gargron I work for Swiss Broadcast Company. Our devs did a wonderfull job in this regard. I get autotranslated subtitles that are amazingly good. It ain't literature but very good. It's a two tier system that joins the captions, then translation and then reconstructing the captions. Translation is done by Claude. Langs are not that big of a challange (DE FR IT EN). Only Rumantsch is a challange. Claude 3.5(!) Is pretty darn good though. Claude 4+ not so much
John Abbe (aka Slow)@decurtins @ErikUden @Gargron One Apertus focus is being multilingual, it may do a better job with Rumantsch. https://www.swiss-ai.org/apertus
xirah@decurtins @ErikUden @Gargron
The things is that only people who speak the translated language sufficiently well, can assess the validity of the translation. So in specialist's hands the machine translation has some value. Still a nogo for literature.
Edit: typos
The things is that only people who speak the translated language sufficiently well, can assess the validity of the translation. So in specialist's hands the machine translation has some value. Still a nogo for literature.
Edit: typos
Alexander Bochmann@Gargron Machine translated UIs are even worse a crime. LLMs don't have the slightest idea of the context of some random button, and (looking at Microsoft's German UI translations recently) seem to choose the worst possible word to drop into that.
Tom
Christian Sarnataro@tdelmas This doesn't mean it was translated with an LLM, though. Very often human translators, especially in tech, have to translate a single label with no context around it, usually they try to be generic enough that the label can be used in many places unchanged. But sometimes that exact label has a slightly different meaning n different contexts, like in your example.
Gustavo@galaxis @Gargron To be fair, it happens with human translations too: I fixed some translations in open-source projects in which the translation interface only showed the text, but not the context, and the previous translator translated it wrongly. Example: Wikipedia had "Large (width)" (Largo) translated to "Huge" (Grande). If you check the edit history for this entry in Wikimedia, that's my name fixing this issue. But, sure, it's mostly common in machine translations, as I commented in some other toot in this thread.