Skip to content
  • Hjem
  • Seneste
  • Etiketter
  • Populære
  • Verden
  • Bruger
  • Grupper
Temaer
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Kollaps
FARVEL BIG TECH
  1. Forside
  2. Ikke-kategoriseret
  3. Machine translations are often brought up as a gotcha whenever I criticize LLMs.

Machine translations are often brought up as a gotcha whenever I criticize LLMs.

Planlagt Fastgjort Låst Flyttet Ikke-kategoriseret
255 Indlæg 170 Posters 0 Visninger
  • Ældste til nyeste
  • Nyeste til ældste
  • Most Votes
Svar
  • Svar som emne
Login for at svare
Denne tråd er blevet slettet. Kun brugere med emne behandlings privilegier kan se den.
  • gargron@mastodon.socialG gargron@mastodon.social

    Machine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.

    jfparis@rouge.eu.orgJ This user is from outside of this forum
    jfparis@rouge.eu.orgJ This user is from outside of this forum
    jfparis@rouge.eu.org
    wrote sidst redigeret af
    #37

    @Gargron Translation is real hard work.

    It takes some real work to get all the nuances and some of the things you write in one language can take real effort not to sound utter BS in another.

    Become even harder when you want to keep this through a longer document (literature as you said but not only)

    LLM is a great solution though for a person that wants to get the work done and have "a product" in a language that they don't understand 🙂

    1 Reply Last reply
    0
    • gargron@mastodon.socialG gargron@mastodon.social

      I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

      datarama@hachyderm.ioD This user is from outside of this forum
      datarama@hachyderm.ioD This user is from outside of this forum
      datarama@hachyderm.io
      wrote sidst redigeret af
      #38

      @Gargron I've read translations of Haruki Murakami's novels in English and my native Danish - and I've found the latter *far* better. I can't judge the fidelity to the originals because I don't speak Japanese, but at least my reading experience with the Danish translations were a lot better - and I've probably read at least ten times as much English in my life as Danish.

      I learned a while ago that the Danish translator of most (possibly all) Murakami's books has lived in Japan, knows Murakami personally, and talks to him about her translation work. And, well, the level of care put into those translations really shows.

      wonka@chaos.socialW 1 Reply Last reply
      0
      • virgilpierce@nerdculture.deV virgilpierce@nerdculture.de

        @Gargron plus doesn't everyone do the test of translate then translate back? They are garbage in a way that even a machine could recognize as garbage.

        gdinwiddie@mastodon.socialG This user is from outside of this forum
        gdinwiddie@mastodon.socialG This user is from outside of this forum
        gdinwiddie@mastodon.social
        wrote sidst redigeret af
        #39

        @virgilpierce @Gargron
        There's an old joke from the 1960s about machine translation of the saying "the spirit is willing, but the flesh is weak" from English to Russian and then back again.
        The result was "the vodka is good but the meat is rotten."

        wonka@chaos.socialW szescstopni@circumstances.runS 2 Replies Last reply
        0
        • gargron@mastodon.socialG gargron@mastodon.social

          I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

          mayank@front-end.socialM This user is from outside of this forum
          mayank@front-end.socialM This user is from outside of this forum
          mayank@front-end.social
          wrote sidst redigeret af
          #40

          @Gargron 💯 languages are usually not 1:1, and translation is impossible to automate without butchering the original meaning.

          bad translation really sticks out when you understand both languages. even if it's serviceable enough to get the core meaning across, it might fail to capture the tone, the cultural references, and the full weight.

          i have a lot of respect for people who create good subtitles that try to preserve the original intent, even when it sometimes feels impossible.

          1 Reply Last reply
          0
          • gargron@mastodon.socialG gargron@mastodon.social

            Machine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.

            benroyce@mastodon.socialB This user is from outside of this forum
            benroyce@mastodon.socialB This user is from outside of this forum
            benroyce@mastodon.social
            wrote sidst redigeret af
            #41

            @Gargron

            on the plus side, machine translation illuminated me as to the involvement of the presbyterian church in the famous movie "Star War the Third Gathers: Backstroke of the West"

            https://en.wikipedia.org/wiki/Star_Wars:_Episode_III_%E2%80%93_Revenge_of_the_Sith#Backstroke_of_the_West

            sonikku@techhub.socialS 1 Reply Last reply
            0
            • cstross@wandering.shopC cstross@wandering.shop

              @Gargron I'm willing to guess that machine translation of prose may serve two uses: firstly, as an assist for human translators (by preparing a very rough first cut, which they then have to refine), and secondly, as an assist for human editors in figuring out which foreign-language-works to pay a human translator (with or without AI assistance) to work on (translation costs money: knowing where to spend it is important). But those are assistive roles, not human-replacing ones.

              jgg@qoto.orgJ This user is from outside of this forum
              jgg@qoto.orgJ This user is from outside of this forum
              jgg@qoto.org
              wrote sidst redigeret af
              #42

              @cstross @Gargron

              I feel pretty dumb telling this to the master, but translating a literary work is much more than changing one word for another. Even it you keep all the meaning, it gets weird and doesn't flow; each language has its own rhythm and cadence. A good translator frequently has to completely rewrite a paragraph to keep the sense, the emotions and the flow of the story. Even worse, he needs to make it faithful to the original, which having intermediate versions can make harder.

              I'm not a professional translator, but I have tried to translate some public domain stories, and found that automatic translation is a hindrance. I had to rewrite nearly all, looking always to the original version. It was too easy to drift far from it and get the text and the author absolutely distorted.

              It is a work of art and love, not something a machine can do at all. Not even a part of it.

              1 Reply Last reply
              0
              • gargron@mastodon.socialG gargron@mastodon.social

                I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

                etchedpixels@mastodon.socialE This user is from outside of this forum
                etchedpixels@mastodon.socialE This user is from outside of this forum
                etchedpixels@mastodon.social
                wrote sidst redigeret af
                #43

                @Gargron In addition a lot of anglophone people speak only one language, so they've never been able to compare the translation of a book between two languages they speak.

                1 Reply Last reply
                0
                • benroyce@mastodon.socialB benroyce@mastodon.social

                  @Gargron

                  on the plus side, machine translation illuminated me as to the involvement of the presbyterian church in the famous movie "Star War the Third Gathers: Backstroke of the West"

                  https://en.wikipedia.org/wiki/Star_Wars:_Episode_III_%E2%80%93_Revenge_of_the_Sith#Backstroke_of_the_West

                  sonikku@techhub.socialS This user is from outside of this forum
                  sonikku@techhub.socialS This user is from outside of this forum
                  sonikku@techhub.social
                  wrote sidst redigeret af
                  #44

                  @benroyce @Gargron back in the day I had a bootleg DVD of The Two Towers with the best subtitles China could do.

                  benroyce@mastodon.socialB A dudinka@mastodon.worldD 3 Replies Last reply
                  0
                  • sonikku@techhub.socialS sonikku@techhub.social

                    @benroyce @Gargron back in the day I had a bootleg DVD of The Two Towers with the best subtitles China could do.

                    benroyce@mastodon.socialB This user is from outside of this forum
                    benroyce@mastodon.socialB This user is from outside of this forum
                    benroyce@mastodon.social
                    wrote sidst redigeret af
                    #45

                    @Sonikku @Gargron 😂

                    1 Reply Last reply
                    0
                    • gargron@mastodon.socialG gargron@mastodon.social

                      I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

                      denofearth@mas.toD This user is from outside of this forum
                      denofearth@mas.toD This user is from outside of this forum
                      denofearth@mas.to
                      wrote sidst redigeret af
                      #46

                      @Gargron
                      And it's not just expressions and turns of phrase, which are unique not only to each language but easily to each region.

                      It's words. There is often no exact match. Many words in one language are not a precise correspondence to those in another.

                      So an elegant turn of phrase in one becomes a wordy explanation in the other. Or a misinterpretation.

                      Only someone fluent in both languages can convey the true meaning accurately and eloquently.

                      1 Reply Last reply
                      0
                      • gargron@mastodon.socialG gargron@mastodon.social

                        I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

                        grb090423@mastodon.socialG This user is from outside of this forum
                        grb090423@mastodon.socialG This user is from outside of this forum
                        grb090423@mastodon.social
                        wrote sidst redigeret af
                        #47

                        @Gargron

                        Well said. 👍

                        1 Reply Last reply
                        0
                        • shunra@wandering.shopS shunra@wandering.shop

                          @cstross @Gargron
                          and the sort of awards that give a book the sheen of "worth reading".

                          My cred: I've translated more books than I can carry. Both fiction and technical.
                          My current position is that use of AI in translation is malpractice.

                          highlandlawyer@mastodon.socialH This user is from outside of this forum
                          highlandlawyer@mastodon.socialH This user is from outside of this forum
                          highlandlawyer@mastodon.social
                          wrote sidst redigeret af
                          #48

                          @Shunra @cstross @Gargron
                          My go-to example is the Esperanto translation of Alice Through The Looking Glass published by Evertype, which has 5 different translations of "Jabberwocky", each of which is absolutely "correct" and each of which is totally different from each other. Even the names of the poem differ.
                          In each case one can see the decisions the translator made balancing meter, rhyme, meaning, implications & nuance of the text, based on what it meant to them; how can a computer do that?

                          brhfl@digipres.clubB 1 Reply Last reply
                          0
                          • gargron@mastodon.socialG gargron@mastodon.social

                            Machine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.

                            stuartb@social.teamb.spaceS This user is from outside of this forum
                            stuartb@social.teamb.spaceS This user is from outside of this forum
                            stuartb@social.teamb.space
                            wrote sidst redigeret af
                            #49

                            @Gargron Many years ago, while on holiday in Amsterdam, I bought a Dutch translation of a book by one of my favourite authors, Terry Pratchett.
                            In it, there was an essay, in English, by Terry, about his struggles to find a translator for the book, which was only accomplished when he realised that it wasn't just a case of taking the text and replacing it with Dutch.
                            No, large sections would have to be entirely re-written by the translator, to use concepts that a Dutch audience would find familiar.
                            And not just in Dutch, but every language.
                            The example he gave was one character who was experiencing the feeling of being stuck in traffic on a busy road on a Sunday afternoon, and after miles of driving, finding that the cause of the tailback was a little old lady out for her weekly drive to church in her trusty old Morris Marina, never getting above 20 MPH becuase it felt too fast.
                            This is something that British people are well acquanted with, but the Dutch translator had to come up with a completely different way of explaining this, because it's not something particularly prevalant over there.
                            It's not just about translating the words, its translating the feelings, the emotions, to something readers in another place will understand.
                            And LLM's fail spectacularly at that.

                            vfrmedia@social.tchncs.deV mikefromlfe@cupoftea.socialM venite@mastodon.nlV 3 Replies Last reply
                            0
                            • gargron@mastodon.socialG gargron@mastodon.social

                              I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

                              aeva@mastodon.gamedev.placeA This user is from outside of this forum
                              aeva@mastodon.gamedev.placeA This user is from outside of this forum
                              aeva@mastodon.gamedev.place
                              wrote sidst redigeret af
                              #50

                              @Gargron I think anglophones experience start difference between good and bad translations more often through video games

                              gabboman@gabboman.xyzG qgustavor@urusai.socialQ 2 Replies Last reply
                              0
                              • gargron@mastodon.socialG gargron@mastodon.social

                                Machine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.

                                dat@social.g33ky.deD This user is from outside of this forum
                                dat@social.g33ky.deD This user is from outside of this forum
                                dat@social.g33ky.de
                                wrote sidst redigeret af
                                #51
                                @Gargron and then there's the question on how it's used

                                see firefox that generated new translations and threw awai human written ones
                                jrdepriest@infosec.exchangeJ 1 Reply Last reply
                                0
                                • gargron@mastodon.socialG gargron@mastodon.social

                                  Machine translations are often brought up as a gotcha whenever I criticize LLMs. It's worth pointing out two things: Machine translations existed decades before LLMs, and yes, machine translations are useful. However: I would never in my life read a machine translated book. Understanding what a social media post is talking about in rough terms? Sure. Literature? Absolutely not. Hell, have you ever seen machine translated subtitles? It's absolute garbage.

                                  clement@sciences.socialC This user is from outside of this forum
                                  clement@sciences.socialC This user is from outside of this forum
                                  clement@sciences.social
                                  wrote sidst redigeret af
                                  #52

                                  @Gargron As an LLM would say to a translator: "All your job are belong to us".

                                  brad@1040ste.netB 1 Reply Last reply
                                  0
                                  • gargron@mastodon.socialG gargron@mastodon.social

                                    I have the impression that primarily anglophone people don't read as much translated literature, because so much good literature already exists in their language, so this issue may not be as familiar within that demographic. As someone who did not grow up anglophone, I can tell you there is a world of difference between a good and a bad translation even when done by humans. Machine translations are not even on the scale.

                                    juandesant@mathstodon.xyzJ This user is from outside of this forum
                                    juandesant@mathstodon.xyzJ This user is from outside of this forum
                                    juandesant@mathstodon.xyz
                                    wrote sidst redigeret af
                                    #53

                                    @Gargron to make matters worde, at least in the UK when you buy a DVD it only comes with English audio, English audio with descriptions, and maybe original audio, and just English subtitles, and English for the hard of hearing. That’s it. But in Spain, the same DVD, locked to the same region, carried the original audio, audio described English audio, Spanish dubbing, German dubbing, Italian dubbing… and all those languages in subtitles, plus some more.

                                    So it is really difficult for them to be exposed to non-English content,

                                    juandesant@mathstodon.xyzJ 1 Reply Last reply
                                    0
                                    • tubemeister@mstdn.socialT This user is from outside of this forum
                                      tubemeister@mstdn.socialT This user is from outside of this forum
                                      tubemeister@mstdn.social
                                      wrote sidst redigeret af
                                      #54

                                      @aeduna @Gargron Oh yes. Translating the story is one thing, but especially with Pratchett it’s only half the story.

                                      Puns are horrible to translate, you either just skip them because they just don’t work, or you go to extremes to wring some kind of joke out of them.

                                      There isn’t necessarily a right approach here. This particular Pratchett translation apparently skipped a lot, but I also remember a HHGTTG translation that took the “a joke at *any* cost” path and um.

                                      1 Reply Last reply
                                      0
                                      • sonikku@techhub.socialS sonikku@techhub.social

                                        @benroyce @Gargron back in the day I had a bootleg DVD of The Two Towers with the best subtitles China could do.

                                        A This user is from outside of this forum
                                        A This user is from outside of this forum
                                        avincentinspace@furry.engineer
                                        wrote sidst redigeret af
                                        #55

                                        @Sonikku there is absolutely no way this is real

                                        sonikku@techhub.socialS 1 Reply Last reply
                                        0
                                        • sonikku@techhub.socialS sonikku@techhub.social

                                          @benroyce @Gargron back in the day I had a bootleg DVD of The Two Towers with the best subtitles China could do.

                                          dudinka@mastodon.worldD This user is from outside of this forum
                                          dudinka@mastodon.worldD This user is from outside of this forum
                                          dudinka@mastodon.world
                                          wrote sidst redigeret af
                                          #56

                                          @Sonikku @benroyce @Gargron

                                          this kind of bad translations /autosubtitles is the best comedy to my neurodivergent brain.

                                          i speak several languages and always try to find out where it went wrong too, so it's educating too 🙂

                                          benroyce@mastodon.socialB 1 Reply Last reply
                                          0
                                          Svar
                                          • Svar som emne
                                          Login for at svare
                                          • Ældste til nyeste
                                          • Nyeste til ældste
                                          • Most Votes


                                          • Log ind

                                          • Har du ikke en konto? Tilmeld

                                          • Login or register to search.
                                          Powered by NodeBB Contributors
                                          Graciously hosted by data.coop
                                          • First post
                                            Last post
                                          0
                                          • Hjem
                                          • Seneste
                                          • Etiketter
                                          • Populære
                                          • Verden
                                          • Bruger
                                          • Grupper