Show HN: Unlimited machine translation API for $200 / Month

Post by alexei_rudak » Wed, Jun 01, 2022, 5:34 PM UTC

bruce343434 wrote: post #23

request a demo?

Post by TinoDidriksen » Wed, Jun 01, 2022, 8:09 PM UTC

sshine wrote: post #10

lajamerr wrote: post #3

I've been following machine translation for the past 8 years or so just as a consumer and I still haven't found anything that provides out-of-the-box good results, everything requires still heavy manual editing/complete rewrites of sentences. Source Text: 俺は34歳住所不定無職。 人生を後悔している真っ最中の小太りブサメンのナイスガイだ。 つい三時間ほど前までは住所不定ではない、ただの引きこもりベテランニートだったのだが、気付いたら親が死んでおり、引きこもっていて親族会議に出席しなかった俺はいないものとして扱われ、兄弟たちの奸計にハマり、見事に家を追い出された。 Machine…

I used to keep track of the state of machine translation some years back. I think the way you measure the success of an automated translation is edit distance, i.e. how many manual edits you need to make to a translated text before you reach some acceptable state. I suppose it's somewhat subjective, but it is possible to construct a benchmark and allow for multiple correct results. The best resources I knew back then…

Post by MauroIksem » Wed, Jun 01, 2022, 10:58 PM UTC

rhesa wrote: post #17

My litmus test for translation services is to see if the ambiguity between "turkey" (the bird) and "Turkey" (the country) manifests itself. Many European languages have two separate words for the two concepts that can't possibly be confused, so I think this is a good unit test. My Dutch test sentence is: "de kalkoen bezoekt Turkije" (the bird visits the country). Most of them get it wrong for most European languages:…

Post by sshine » Thu, Jun 02, 2022, 8:07 AM UTC

TinoDidriksen wrote: post #33

sshine wrote: post #10

Earlier quoted context omitted.

I used to keep track of the state of machine translation some years back. I think the way you measure the success of an automated translation is edit distance, i.e. how many manual edits you need to make to a translated text before you reach some acceptable state. I suppose it's somewhat subjective, but it is possible to construct a benchmark and allow for multiple correct results. The best resources I knew back then…

The VISL translator is not CG-3 - it's GramTrans, with the commercial vendor being GrammarSoft ApS. CG-3 is merely one of the general purpose langtech tools used in the pipeline. Apertium also uses CG-3. Both GramTrans and Apertium are rule-based. Very similar technology. (I wrote CG-3, and work for both GrammarSoft and Apertium.)