> Ich benutze (I am using) [ikh benoot-se]
GPT4 (GPT4) [ge-pe-te-fear]
um Text (to reformat text) [oom tekst]
aus Englisch (from English) [aus engl-ish]
zu Japanisch (to Japanese) [tsoo yap-an-ish]
in einfachem Lesemodus (in easy reading mode) [in ine-fakh-em leh-se-moh-dus]
umzuformatieren (to reformat) [oom-tsoo-for-ma-teer-en].
Es ist sehr (It is very) [es ist zehr]
gut für (good for) [goot fuhr]
Sprachstudium (language study) [shprakh-shtoo-dee-oom]
mit interessanten (using interesting) [mit int-er-es-sant-en]
Themen (topics) [tay-men].
The prompt I used:
Create a Japanese easy reading mode version of the given English, breaking it into 2-4 word chunks, providing romaji and English translations in brackets for each phrase. This is intended for language study purposes.
~~
Of course this is just a reader prompt, we could also have chat mode, asking clarifying questions, asking for more examples of a phrase, generate quizzes, etc.
I am at this weird point where I know phonetically much more than I can read. This formatting helps a lot because you get to see the Kanji first, then you use romaji and English only when necessary. Being different scripts helps separate them visually so as not to read the romaji before I want to.
Do you usually use GPT4 to translate from English, or was that just for the example in your comment? Because the translated output highlights the major problem of this learning-through-AI approach: The generated output can just simply be wrong, like it is here (both the Japanese and German).
I think it is good enough to "break into" the text. It's not the most literary translation but you could just start from a Japanese text if that's what you wanted. I went for modding the English text I am currently reading as a language exercise.
As long as learners are aware, I agree. Getting you to the point where you can start reading "regular" texts in a language is worth it even if some of what you think you know at the point you get there is wrong.
The Ich -> ikh transliteration is wrong. Of course there are a bunch of German photetics which you can't translate into direct English transliterations because the sound inventory is different.
That being said, GPT is still pretty powerful for language learning but you really have to verify more than you trust.
es gibt den 'ch' Laut nicht isoliert im Englischen, so wie es das Sean Connery sh nicht im Deutschen gibt. (also ch wie in ich oder nicht, nicht ch wie in ach)
sehr nahe dem ich-ch käme das ch aus much, halt ohne das t davor, mut-sh, aber auch nicht ganz.
alle Sprachen haben Laute die es in anderen Sprachen einfach nicht gibt, und manche davon sind auch nach einem gewissen Alter nur noch schwer zu lernen. mein Liebling waren glottale plosive aus dem Arabischen.
aber danke für den Hinweis, ja, auch ish ist nur eine Annäherung.
The closest English equivalent I can think of is the first sound in the word "huge" if it's pronounced with a lot of exaggeration. Even that's not a perfect match.
German 'ch' in ich is a fricative, like sh in fish. or the chute in parachute.
cute starts with a plosive, a click/plop sound, like check, TikTok curfew etc
edit: I'm talking about the german "ich" meaning I, self-reference, not about how to read that word as if it was an English word, rhyming with ick(y), there you're of course correct.
I am using GPT4 to reformat text from English to Japanese in easy reading mode. It is very good for language study using topics of interest.
> 私は (Watashi wa) [I am] GPT4を使って (GPT4 o tsukatte) [using GPT4] 英語から (Eigo kara) [from English] 日本語へ (Nihongo e) [to Japanese] 簡単な読み物 (Kantan na yomimono) [easy reading mode] に変換します。 (ni henkan shimasu) [to reformat] それは (Sore wa) [It is] 興味深いトピック (Kyoumi bukai topikku) [interesting topics] を使って (o tsukatte) [using] 言語学習 (Gengo gakushuu) [language study] にとても良い (ni totemo yoi) [very good] です。 (desu) [is]
Same, but in German:
> Ich benutze (I am using) [ikh benoot-se] GPT4 (GPT4) [ge-pe-te-fear] um Text (to reformat text) [oom tekst] aus Englisch (from English) [aus engl-ish] zu Japanisch (to Japanese) [tsoo yap-an-ish] in einfachem Lesemodus (in easy reading mode) [in ine-fakh-em leh-se-moh-dus] umzuformatieren (to reformat) [oom-tsoo-for-ma-teer-en]. Es ist sehr (It is very) [es ist zehr] gut für (good for) [goot fuhr] Sprachstudium (language study) [shprakh-shtoo-dee-oom] mit interessanten (using interesting) [mit int-er-es-sant-en] Themen (topics) [tay-men].
The prompt I used:
Create a Japanese easy reading mode version of the given English, breaking it into 2-4 word chunks, providing romaji and English translations in brackets for each phrase. This is intended for language study purposes.
~~
Of course this is just a reader prompt, we could also have chat mode, asking clarifying questions, asking for more examples of a phrase, generate quizzes, etc.
I am at this weird point where I know phonetically much more than I can read. This formatting helps a lot because you get to see the Kanji first, then you use romaji and English only when necessary. Being different scripts helps separate them visually so as not to read the romaji before I want to.