this post was submitted on 01 Aug 2026
7 points (73.3% liked)

Language Learning

995 readers
2 users here now

A community all about learning languages!

Ask / talk about a specific language or language learning in general.

Sopuli's instance rules apply

  1. Remember the human! (no harassment, threats, etc.)
  2. No racism or other discrimination
  3. No Nazis, QAnon or similar whackos and no endorsement of them
  4. No porn
  5. No ads or spam
  6. No content against Finnish law

Other active Lemmy language communities:

Other communities outside Lemmy:

Community banner & icon credits:

Icon: The book cover of Babel (2022 novel by R. F. Kuang)

Banner: Epic of Gilgamesh tablet (© The Trustees of the British Museum)

founded 3 years ago
MODERATORS
Lazycog@sopuli.xyz
emb@lemmy.world
7
Why are online translators crap at capturing nuance? (feddit.online)
submitted 6 days ago* (last edited 6 days ago) by animemann80@feddit.online to c/languagelearning@sopuli.xyz
5 comments fedilink hide all child comments
 

I'm not talking about translations of basic dialog such as "How are you?" or "Nice to meet you." from English to let's say Japanese, Mandarin, French, Spanish & whatever. Rather the topic dwells more on translation apps or LLM's failing to capture the nuance of a conversation since words can connotate different definitions as well as being understood differently when applied.

Take the word 蛇行 (だこう) which is defined as amongst the lines of "meandering" but when compounded with 蛇行運転 for example, the definition leans closer to "erratic driving" but most online translatiors mess this up on saying "driving in a serpentine manner" which sounds stupid. No wonder why Japanese is hard for LLM's to work with.

you are viewing a single comment's thread
view the rest of the comments
[–] FinjaminPoach@lemmy.world 3 points 6 days ago* (last edited 6 days ago)

Which ones have you used / use the most / have the most gripes with? Other people might be able to point you in the right direction for a good one.

DeepL and Google trnpanslate are the two I know, and I only use deepL now. Don't remember the names of any others.

As for actually why, well I seem to remember google translate was focused on nuance but seemed to fall off or outright regress in quality since LLMs have become a thing.

They should come up with one box for literal meaning and contextual meaning. You could highlight bits and then have the interface translate just that section. The software is woefully inept for so useful a service 🥲