Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

arsastronomica.com

Post reply on HN
Print view View original

51–60 of 67 posts

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#51

Post by sweisman »

bawolff wrote: post #39
domschl wrote: post #4

Why was the comment of the author of the translation-site that explains the methodology flagged / dead? The mere fact that the translation was AI-assisted shouldn't be a reason to flag a comment. AI translations, especially supervised translations, can actually achieve a reasonable level of quality. Disagreement on AI philosophy shouldn't be a reason to flag a contribution.

> AI translations, especially supervised translations, can actually achieve a reasonable level of quality. That may be true, but also not really what i'm worried about. With AI on an ancient book written from a world view very different from the contemporary one, i'd worry more about misleading translations.

Misleading in what way?

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#52

Post by sweisman »

names_are_hard wrote: post #35
sweisman wrote: post #7

Earlier quoted context omitted.

A professional book editor and Hebrew translator said the translation of the one work he checked out was "impressive". Others have responded equally positively to the Latin translations. AI as a panacea is overwrought, but there are genuine positive uses of it. Would critics rather have NO translations of these pivotal works?

I'm not a book editor or translator, just a guy with a reasonable familiarity with rabbinic literature in its original language. I spent some time reading the translation of Tzemach David, and I can say the following: it's legible to me but the AI is clearly lacking a style guide. It's inconsistent about what it chooses to translate and what it chooses to transliterate, and when it transliterates, it's inconsistent i…

Can you email me with more info? It is likely the distinctions you noted are from the source. There is a glossary maintained that keeps specific words or phrases consistent. But slightly different phrases can resolve in inconsistent ways.

The problem is not the AI, but rather a weakness in the design. In other words, a bug. Or a regression and we call them today. It is fixable.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#53

Post by sweisman »

mondainx wrote: post #43

Don't get me wrong, this is awesome, but it could be better by adding Greek and Arabic, and possibly Sumerian documents?

Thank you. I have considered Arabic, as there a couple works I am interested in.

My queue of Hebrew and Latin works is already lengthy, and this is my focus for now.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#54

Post by flir »

sweisman wrote: post #50
flir wrote: post #38

Earlier quoted context omitted.

The thing with LLM-generated code is you can test it on a real CPU - that's a tight feedback loop with a cast-iron verification mechanism. Translations of human language have no analogous mechanism. So yes, the translation might be perfect , but until a human puts their reputation on the line and says "I certify this translation is accurate", it's still shit. It's shit because of the way it was created, not its absol…

I know what I know from experience. You know what you know from nothing at all. Numerous people have commented to me about Hebrew and Latin works, who know what they are talking about, and none has criticized the fidelity of the translation to the source. The criticisms proffered are minor, while the praise extensive. A couple years ago, I shared your opinion. Now I don't. You are the one who won't change your mind.…

> You know what you know from nothing at all.

I've done it myself. Transcription of 19th century newspaper articles to markdown, mostly. Some earlier wills (which were an absolute pig - secretary hand). Oh, and categorisation of postcards. That's why I was poking around your pipeline - to see if I could learn anything. You're right, tabular data is hard. Also columns, and proper nouns.

Feeding the LLM a context-aware cheat sheet helped with the nouns. BTW, what I said about using multiple models for parallax was good advice.

Do you know you're very spiky?

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#55

Post by bawolff »

sweisman wrote: post #51
bawolff wrote: post #39

Earlier quoted context omitted.

> AI translations, especially supervised translations, can actually achieve a reasonable level of quality. That may be true, but also not really what i'm worried about. With AI on an ancient book written from a world view very different from the contemporary one, i'd worry more about misleading translations.

Misleading in what way?

AI is famous for hallucinating and misunderstanding subtle points, especially when you get away from the typical stuff it is trained on.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#56

Post by bawolff »

sweisman wrote: post #50
flir wrote: post #38

Earlier quoted context omitted.

The thing with LLM-generated code is you can test it on a real CPU - that's a tight feedback loop with a cast-iron verification mechanism. Translations of human language have no analogous mechanism. So yes, the translation might be perfect , but until a human puts their reputation on the line and says "I certify this translation is accurate", it's still shit. It's shit because of the way it was created, not its absol…

I know what I know from experience. You know what you know from nothing at all. Numerous people have commented to me about Hebrew and Latin works, who know what they are talking about, and none has criticized the fidelity of the translation to the source. The criticisms proffered are minor, while the praise extensive. A couple years ago, I shared your opinion. Now I don't. You are the one who won't change your mind.…

> Numerous people have commented to me about Hebrew and Latin works, who know what they are talking about, and none has criticized the fidelity of the translation to the source.

Have these people gone on the record saying that? What are their credentials?

I got to be honest, claims that some unnamed person privately told you they thought your product was good is pretty meaningless. I feel like that makes me trust you less not more.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#57

Post by sweisman »

flir wrote: post #54
sweisman wrote: post #50

Earlier quoted context omitted.

I know what I know from experience. You know what you know from nothing at all. Numerous people have commented to me about Hebrew and Latin works, who know what they are talking about, and none has criticized the fidelity of the translation to the source. The criticisms proffered are minor, while the praise extensive. A couple years ago, I shared your opinion. Now I don't. You are the one who won't change your mind.…

> You know what you know from nothing at all. I've done it myself. Transcription of 19th century newspaper articles to markdown, mostly. Some earlier wills (which were an absolute pig - secretary hand). Oh, and categorisation of postcards. That's why I was poking around your pipeline - to see if I could learn anything. You're right, tabular data is hard. Also columns, and proper nouns. Feeding the LLM a context-aware…

No, because I don't know what spiky means.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#58

Post by names_are_hard »

sweisman wrote: post #52
names_are_hard wrote: post #35

Earlier quoted context omitted.

I'm not a book editor or translator, just a guy with a reasonable familiarity with rabbinic literature in its original language. I spent some time reading the translation of Tzemach David, and I can say the following: it's legible to me but the AI is clearly lacking a style guide. It's inconsistent about what it chooses to translate and what it chooses to transliterate, and when it transliterates, it's inconsistent i…

Can you email me with more info? It is likely the distinctions you noted are from the source. There is a glossary maintained that keeps specific words or phrases consistent. But slightly different phrases can resolve in inconsistent ways. The problem is not the AI, but rather a weakness in the design. In other words, a bug. Or a regression and we call them today. It is fixable.

I think that I might not have been clear enough. Of course Rosh mesivta and exilarch differ in the source, but I don't think a human translator would choose to translate one title and not the other. In circles where people use the word exilarch I am almost 100% positive no one would say Rosh mesivta, and the kind of folks who use Rosh mesivta in conversation would say Reish Galusa, not exilarch.

I can't imagine that metivta and mesivta are not both transliterations of the word מתיבתא.

You need to identify the target audience and stick to their language. Are you translating for a general lay audience? An academic audience? Contemporary religious Jews? If the latter, is it a yeshivish audience or a wider group? How much familiarity with Hebrew is expected from the reader?

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#59

Post by sweisman »

names_are_hard wrote: post #58
sweisman wrote: post #52

Earlier quoted context omitted.

Can you email me with more info? It is likely the distinctions you noted are from the source. There is a glossary maintained that keeps specific words or phrases consistent. But slightly different phrases can resolve in inconsistent ways. The problem is not the AI, but rather a weakness in the design. In other words, a bug. Or a regression and we call them today. It is fixable.

I think that I might not have been clear enough. Of course Rosh mesivta and exilarch differ in the source, but I don't think a human translator would choose to translate one title and not the other. In circles where people use the word exilarch I am almost 100% positive no one would say Rosh mesivta, and the kind of folks who use Rosh mesivta in conversation would say Reish Galusa, not exilarch. I can't imagine that…

Thank you. Your comments are very helpful. I am working on updating the translation agents and fixing the issue in the existing works.

If you'd like, you can contact me privately and I will let you know when the updates are published. Or just check the site occasionally for updates.

Re: Ars Astronomica – English translations of rare Hebrew and Latin astronomy texts

#60

Post by sweisman »

flir wrote: post #54
sweisman wrote: post #50

Earlier quoted context omitted.

I know what I know from experience. You know what you know from nothing at all. Numerous people have commented to me about Hebrew and Latin works, who know what they are talking about, and none has criticized the fidelity of the translation to the source. The criticisms proffered are minor, while the praise extensive. A couple years ago, I shared your opinion. Now I don't. You are the one who won't change your mind.…

> You know what you know from nothing at all. I've done it myself. Transcription of 19th century newspaper articles to markdown, mostly. Some earlier wills (which were an absolute pig - secretary hand). Oh, and categorisation of postcards. That's why I was poking around your pipeline - to see if I could learn anything. You're right, tabular data is hard. Also columns, and proper nouns. Feeding the LLM a context-aware…

The biggest problem with hallucinations (or confabulations as Claude prefers haha) is from tables. Prose has context that anchors it.

Hebrew is also much worse than Latin, which uses Arabic numerals. Hebrew conventionally uses the letters for numeric representation too.

I am getting good (and improving results), but the token cost is heavy.

Post reply on HN