February 3rd, 2025

How Translation Works, Book Title Edition

John Scalzi emphasizes the importance of human translators in fiction translation, highlighting the need to capture tone and cultural nuances, as illustrated by the Hungarian title of his book.

Read original articleLink Icon
FrustrationAppreciationSkepticism
How Translation Works, Book Title Edition

John Scalzi discusses the complexities of translating fiction, emphasizing that it involves more than direct word-for-word conversion. Effective translation captures the tone and cultural nuances of the original text, which is crucial for conveying the intended feel to the audience. He illustrates this with the Hungarian title of his book "When the Moon Hits Your Eye," which was changed to "Csak a hold az égen," a phrase from a popular Hungarian song. This title resonates more with Hungarian readers, evoking a similar emotional response as the original English title. Scalzi argues that human translators are essential for this process, as they understand cultural contexts and emotional subtleties that machines cannot replicate. He has included clauses in his contracts to ensure that translations are done by humans rather than relying on automated systems. While he acknowledges that not all translations have been successful, he trusts local publishers to make appropriate choices for their markets. The discussion highlights the importance of human insight in translation, particularly for literary works where emotional impact is key.

- Translating fiction requires capturing tone and cultural nuances, not just direct translation.

- The Hungarian title change for Scalzi's book illustrates the importance of local cultural references.

- Human translators are essential for conveying emotional subtleties that machines cannot replicate.

- Scalzi includes clauses in contracts to ensure translations are done by humans.

- Trusting local publishers is crucial for successful title translations in different markets.

AI: What people are saying
The comments reflect a range of opinions on the challenges and future of translation, particularly in literature.
  • Human translators face immense time pressure, leading to errors that can alter the meaning and tone of translations.
  • Examples of poor translations highlight the importance of cultural context and familiarity with source material.
  • There is a debate about the role of AI in translation, with some suggesting a collaborative approach between AI and human translators.
  • Some commenters believe that advancements in AI could eventually produce translations that rival human efforts.
  • The nuances of language and cultural references are emphasized as critical elements that current AI struggles to capture.
Link Icon 10 comments
By @krisoft - 3 months
That being sad human translators are very often under imense time pressure and that sadly leaves a mark on the translations.

To stay with hungarian example: in the original of Fifty Shades Of Grey Christian is a big fan of the band Kings of Leon. Somehow the translator managed to translate the band name as Lion King. Which drastically changed the vibe of some scenes. Most probably the translator wasn’t familiar with the band and had to translate it super fast.

Similarly in the hungarian translation of Harry Potter Slytherin's Locket was translated as Slytherin's Lock. And when in the next book the context made it clear that indeed we are talking about a locket not a lock they just changed the name of the item like nothing happened. :)

By @RheingoldRiver - 3 months
This is the only thing I think of now when I hear "that's amore" - https://www.nytimes.com/2021/06/22/science/moray-eels-eat-la...
By @rererereferred - 3 months
Sometimes translators make weird decisions. Ocean's eleven in Latam Spanish was "La gran estafa" (The great swindle), which to me sounded much more generic, then came Ocean's twelve and they called it "La nueva gran estafa" (The new great swindle). On the 3rd movie they had to give in and called it "Ahora son 13" (Now they are 13), losing the connection to the others completely. For the next one they didn't even bothered and called it "Ocean's 8: las estafadoras" (Ocean's 8: The swindlers).

Bonus: the original movie from the 60s was named "Once a la medianoche" (Eleven at midnight). I would have preferred they kept that name.

By @tkgally - 3 months
This is a nice essay, with an excellent example of the challenges and art of literary translation. But the author seems to assume that "computer translation" is limited to services like Google Translate or DeepL: put in a text, get a translation, with no consideration of the context or purpose. Properly prompted LLMs yield much better results and are already helping human translators produce better translations than they could on their own. Whether a completely automated workflow is possible for translating literary texts in an artful and engaging way—I don't know. But I wouldn't reject that possibility out of hand.

Addendum: The above comment has received at least two up votes and two down votes: in the hour after I posted it, I saw it go from 1 point to 3 points and back to 1. Perhaps people who disapprove of it could say why?

By @romaaeterna - 3 months
On this subject, it is worth reading Tolkien's letters to publishers and translators about the translation choices regarding his works. His philology comes into full play.
By @thomassmith65 - 3 months
We're already not far from being able to do something like...

(Dean Martin "That's Amore") - (English) + (Hungarian)

https://kawine.github.io/blog/nlp/2019/06/21/word-analogies....

By @IsaacZerh - 3 months
"Common phrases in one language don’t exist in another; cultural references in one country mean nothing elsewhere, and so on. This is why a computerized translation is fine for a bland business email but will utterly fail for a novel."

I'm sure it's going to be indistinguishable very soon, if not already.

By @phatnguyen - 3 months
Tech is evolving fast, and while current AI struggles with nuance, humor, and emotional weight, future advancements might surprise us. Maybe the best approach isn’t ‘humans only’ but a synergy where AI handles structure and humans refine the feel?