this post was submitted on 01 Jul 2023
3 points (100.0% liked)

Japanese Language

1403 readers
1 users here now

ようこそJapaneseLanguageへ! 日本語に興味を持てば、どうぞ登録して勉強しましょう!日本語に関係するどのテーマ、質問でも大歓迎します。 This is a community dedicated to the Japanese language. Feel free to come in and ask questions or post your thoughts and opinions about this beautiful language.

Feel free to check out the web archive of r/LearnJapanese's resources if you're looking for more learning material or tools to aid you in your Japanese language journey!

—————————

Remember that you can add furigana to your posts by writing ~{KANJI|FURIGANA}~ like:

~{漢字|かんじ}~ which comes out as:

{漢字|かんじ}

founded 1 year ago
MODERATORS
 

When I mean learning I do not mean translating big sentences or something like that, I mean things like: "Is this japanese sentence correctly written? 雲の日が好きです" In this example it answered: "

Yes, the Japanese sentence "雲の日が好きです" is correctly written. It translates to "I like cloudy days" in English. Here's a breakdown of the sentence:

  • 雲 (くも/kumo): This means "cloud."
  • の (no): This is a possessive particle that indicates the relationship between "cloud" and "day" in this context.
  • 日 (ひ/hi): This means "day."
  • が (ga): This is a subject marker particle that marks "cloudy day" as the subject of the sentence.
  • 好きです (すきです/suki desu): This means "like" or "to like" and is a polite way of expressing one's preference. The verb 好き (suki) means "to like," and です (desu) is a polite copula used to indicate politeness and formality.

Therefore, the sentence "雲の日が好きです" correctly conveys the meaning "I like cloudy days" in Japanese.

"

Is this correct,do you consider it reliable?

Sometimes I also ask some questions like: "What function does 'こと' grammatically fulfill on this sentence? .... "

top 5 comments
sorted by: hot top controversial new old
[–] [email protected] 2 points 1 year ago

Definitely not. ChatGPT is known to "hallucinate", i.e. make things up, so you can't trust that everything it says will be accurate.

[–] [email protected] 1 points 1 year ago

ChatGPT, being generative AI, is strong in fabrication. This is stuff like writing an email, producing a table of contents for a book, creating a python program to spec, or, as DigitalAudio suggested, proofreading.

It is not very strong in fact-checking, or explaining things in a different way. See this recent MDN issue, for example: https://github.com/mdn/yari/issues/9208

[–] [email protected] 1 points 1 year ago* (last edited 1 year ago)

I think ChatGPT works fine for reviewing your text. It will usually manage to point out the bits that sound wrong or inaccurate in your text, and it’s surprisingly precise at doing it.

However, as everybody else pointed out, don’t expect accurate or well-researched answers from it, and take any grammatical or nuanced statements with a mountain of salt, because it’s highly likely that it’s completely wrong.

But I’ve also asked ChatGPT to proofread and adjust my emails for coworkers and clients, and to make sure they sound formal and are respectful enough, and I’ve found it to be very good at this. But I would suggest knowing enough Japanese to be able to fix anything that sounds off or is lost in translation.

I wouldn’t recommend it as a tool for beginners, but I definitely encourage advanced learners to give it a shot, since it really does improve, summarise and rephrase texts successfully a lot of the time.

I don’t remember where I read this first, but I liked this quote:

What’s so confusing about AI is that it’s good at things you wouldn’t expect it to, and it’s terrible at tasks that are stereotypically machine-like. Fact checking? Sourcing? Citations? It’s awful. But writing human-like text? Proofreading? Maintaining natural conversations? It’s awesome at that.

[–] [email protected] 0 points 1 year ago (1 children)

Bing AI is better as it gives sources etc etc

[–] [email protected] 1 points 1 year ago

I was researching a science topic once using bing chat. It gave me absolutely invalid references that didn't even include anything similar to what I was searching for. When I pointed that out, bing apologized and then gave me the same references 🤷