[spondylosaurus]

I recently used a different extension to translate some chapters for a pretty niche manga that'd been dropped by its scanlation team, and the results were definitely readable, but one area where it seemed to struggle a bit was with third-person pronouns (to some confusing results).

IIRC Japanese usually defaults to a generic pronoun that means "that person" rather than more specific pronouns for "he" or "she," so there were some times where I think the AI had to guess on whether "he" or "she" was the appropriate equivalent and just guessed wrong. In at least one instance it might've also been that a character was intentionally using feminine address to refer to an outwardly gay man, which could've been an interesting nuance if translated more clearly, but as things were it just left me confused.

[adibzaini]

Yes, I've tried a few AI translators and the problem is the same. I am working on making the LLM to be aware of the context of the manga as a whole. But still need to make sure there is a balance between quality, speed and cost.

[ryao]

Japanese is far worse than what you describe as far as knowing what anyone means is concerned. Japanese often omits a noun/pronoun entirely and the verb gives no hint as to what it is. In English, we have verb conjugations like “I am”, “he is”, “they are”. In Japanese the same verb is used no matter the subject. Also, “to be” is not even a verb in Japanese, and you just say the thing followed by an end of sentence particle (if you even use that). If you want to say “I am fine”, you simply say “genki (desu/da)” If you want to say someone else is fine and there is sufficient context to indicate the subject, you also just say “genki (desu/da)”.

It is even worse than what I described so far since if the topic of conversation is people’s health, someone might say “Alisu wa” to ask how Alice is and another person would reply “genki (desu/da)” to mean “Alice is well”. “Alisu wa” is just the subject. It is in that context saying “[Is] Alice [well]?”, while only saying the subject. The “wa” part marks it as a subject/topic. English has only a vestigial concept of subject forms of words in I/he/she/they/we. Japanese has much stronger concept of a word that is a subject by appending “wa” to the end of it (or “ga”, but that is a rabbit hole). Thus “Alisu wa” alone is really just saying a subject. In any case, if you are not paying attention, you might mistake the speaker as claiming to be well rather than the speaker claiming someone else is well.

Machine translation often processes text sentence by sentence. That is incapable of determining the subject in a multitude of Japanese sentences since the information needed to determine a subject is in a prior sentence spoken by another person. The machine translator thus must guess and it is often wrong. You will have better luck if you dump text into a high end LLM and ask it to translate since then it will consider prior sentences and have some idea of what each subsequent sentence actually means.

Also, Japanese does not really have more specific pronouns for he and she. Like Chinese, they only have 1 third person pronoun “kare” (he/she/it). In recent years (around the past 160 years from what I have read), it has become popular to use it mainly for males, while the word “kanojo” (girl) is used in its place for females. However, “kanojo” is not a true pronoun and is literally the noun girl. At least, whenever I read “kanojo”, I read girl, not “she”. I suspect machine translators would also read it that way, as it is what is really being said.

That said, I have studied a little Japanese, although I am far from an expert. I replied mainly because your understanding of the translation issue differs strongly from reality. I hope this reply is helpful.

[rjh29]

Japanese is a 'high-context' language which is a big challenge for isolated sentences. The subject is often omitted.

I saw a YouTube comment '中国要素隠す気もないの草' translated to "I don't have any intention of hiding the Chinese elements". The actual translation is "[Ubisoft] aren't even trying to hide the Chinese elements [in Assassin's Creed]". The Japanese sentence has no subject so you need explicit context (in this case the whole content of the video) to translate it correctly.

You also get craziness like 私は美味しい meaning 'I [find the food] delicious' or 'うな重が食い逃げした' meaning '[the person who ate] eel over rice fled without paying'

[ryao]

うな重が食い逃げした does not seem that crazy to me. It is no different than English speakers saying some variation of “it grew legs and walked away”. Usually, that is hyperbole to make a reduction ad absurdem argument about someone stealing. The Japanese phrase interestingly illustrates a use of “ga” (が) as a subject marker, which among other uses, is used that way when reporting new information.

That said, 私は美味しい illustrates how you really need an entirely different way of thinking about language in order to understand Japanese. If you want to report you are tasty as an English speaker might misread that upon hearing は is a subject marker, you would want to use “ga” (が) to mark what is being described as tasty. If you bizarrely want to say you are tasty, like how an English speaker would interpret that upon hearing は means subject, you would want to use が instead of は.

In a slightly more normal but still quite bizarre situation, if you wanted to say you are not tasty, you would say 私が美味しくない. That would be useful if you wanted to tell a Japanese speaking cannibal that you are not tasty. It also would look extremely weird to an English speaker in comparison to the version that declares yourself to be tasty, since two characters were added to the end of tasty to negate it, unlike English where “not” is added before the adjective, but that is how Japanese works.

[uasi]

うな重が食い逃げした doesn't make sense at all. It literally only means that eel over rice itself ate something and fled away.

I think GP meant うな重は食い逃げした. This sentence can be interpreted as the same as above or "[the person] ate eel over rice [but not other dishes] and fled away".

[ryao]

It says that the grilled eel over rice dined and dashed. It sounds like a euphemism to me. It is not very different from saying the grilled eel over rice developed legs and ran away. In either case, you are suggesting someone stole it.

[uasi]

As a Japanese person, I can confidently say that うな重が食い逃げした sounds nonsensical to Japanese ears. The verb 食い逃げ means the subject (うな重 in this case) ate something, not the other way around. Regarding euphemism, you could instead use expressions like うな重が消えた ("うな重 vanished") or うな重が旅立った ("うな重 set off on a journey") to metaphorically describe someone eating their meal.

But... come to think of it, even a native speaker may not be in a position to deny someone's finding about interesting similarities between Japanese and English sentences and possibilities of interpretation.

[uasi]

Yeah, translators would probably lose their minds when they have to translate horribly ambiguous sentences like 今日はウナギ？行くなら行く。 (lit. "Is today an eel? If go, then go."), which means "Are they going to have eel today? If you go with them, I'll go too." or "Today's daily special is eel, isn't it? If you go, I'll go too."