just watched Nagatoro call Senpai a bitch.
it’s lore now, but was totally NOT what she said.
Comment on Crunchyroll & Now Netflix Both Confirm Anime Sub Watchers Are the Minority on Their Platforms
brown567@sh.itjust.works 11 months agoIsn’t translation one of the few actually effective uses for llms? Or am I remembering wrong?
GreenKnight23@lemmy.world 11 months ago
goferking0@lemmy.sdf.org 11 months ago
Aren’t they only doing that so they don’t need to pay for the sub licenses?
Only reason for why they refuse to have subs on their dubs
Duamerthrax@lemmy.world 11 months ago
Not for anything involving art. Real humans flub shit often enough, I don’t trust an llm to convey any important context.
brown567@sh.itjust.works 11 months ago
It seems like my monolingual perspective led me to underestimate the complexity of translating! I have a lot more respect now for the people who do it
nekusoul@lemmy.nekusoul.de 11 months ago If you’re using it just to translate a few paragraphs of text on a website here or there, then yes, it’s much better than what we had before.
For anything complex however it can’t even begin to compare with a professionally done translation/localization. Japanese is one of the more difficult languages to localize due to a bunch of linguistic concepts that don’t translate well to other languages and need creative solutions that carry over the same intent.
More important however is consistency: Even if an AI translates some of the language ticks of the characters instead of completely glossing over them, it needs to do so consistently and apply the same translation across the whole script.
The same goes for any named items. If there’s a “Soul Stone” for example, you need to make sure to call it “Soul Stone” every single time and not “Spirit Rock”.
Khrux@ttrpg.network 11 months ago
I 100% agree on consistency, but I actually suspect LLMs would be pretty decent at translating linguistic concepts. Their grasp of contextual language is always surprisingly good, as seen in how well they rewrite tone to very specific parameters.
I don’t use ChatGPT loads, but I do use it a little, often alongside a method of project that can’t hallucinate. The other week I was talking in one chat about the vocal tone of the novel Blood Meridian by Cormac McCarthy, that has this laconic, worn down dialogue with old testament feeling prose. In another chat, I was prompting ‘sage advice’ for a matcha scone recipe I wanted to make where I was marbling strawberry directly into the dough. I got which chat I was responding in wrong and accidentally had it give me a the scone recipe in Cormac McCarthy’s writing style.
MARBLED SCONES
He measured two cups of flour into a bowl and cut in the baking powder with the side of his hand. Salt followed. It hung in the flour like stone dust. He stirred it with a fork and the dry mix turned over itself and fell still. He cut the butter into cubes and dropped them in and pressed them through with his fingers until the flour took the texture of packed soil. He added a spoon of matcha. The green of river weed. The taste of old things left out in the rain.
He poured in buttermilk and cream. A little at a time. He stirred it slow with a blunt knife and the dough pulled together like it didn’t want to be one thing.
In another bowl he took a handful of flour and mixed it with strawberry powder. A drop of red dye like blood in water. He stirred in cream until it held. He pressed the green dough flat on the counter and laid the red over it and folded. Folded again. The colors turned but did not blend. Like veins of ore in a dark stone.
He shaped the dough into a slab and cut thick rounds with a glass. Each one imperfect. Some leaning. Some split. He set them on a tray lined with paper. The oven was already hot. He did not preheat it. It was always hot. Four twenty five. He watched the scones rise through the glass. They broke along the seams. Green and red and gold. They looked like they’d been dug up.
He split one open while it was still warm. He spread pistachio butter across the inside. It melted into the crumb. Then clotted cream. Then jam. The weight of it brought the top half down slow.
He took it outside and sat in the dirt to eat. There was no sound but the breeze. The sky was wide and empty. The scone was good. The scone was all right.
Now this is actually super easy to critique as a recipe, because it fucking sucks. In adaptation, it’s lost a lot of critical instruction. This is effectively a translation that must adhere to narrow and specific tone to achieve a meaning that cannot be translated without grasping a meaning to language that exists beyond the words.
Obviously this is English to English, but a big difference is that there is far more Japanese out there than Cormac McCarthy.
That being said, nothing cements what you’re saying about consistency more than how badly butchered the underlying instructions to this recipe are.
brown567@sh.itjust.works 11 months ago
True! Consistency is definitely something they aren’t great at
Unboxious@ani.social 11 months ago
Maybe that works if you’re translating large blocks of text, but when it’s small bits of isolated text where the viewer is expected to have visual context which the LLM won’t have it’s a hot mess. I tried experimenting with some translation software on a page of manga and it got a lot of stuff wrong.
brown567@sh.itjust.works 11 months ago
Makes sense!
jacksilver@lemmy.world 11 months ago
As with most AI/LLMs it’s about how much error you can tolerate.
Translating basic info, sure the user can infer any slight mess ups. Translating jokes, idoms, tone, cultural differences, etc. is hard assuming you even got the original text right.