Live data from Hacker News

Show HN: My AI writing assistant for Chinese

unscrambler.dpw.me

1–10 of 29 posts

Show HN: My AI writing assistant for Chinese

#1
Hi HN! In trying to improve my Chinese skills, I built this tool that lets me write a mix of Chinese and English, then recommends a proper Chinese expression. This is super helpful when I want to write something in Chinese but I don't know all the vocab/grammar - I can enter my best effort and use English for the parts I don't know.

Really, the fundamental benefit of the tool is that it encourages me to exercise the writing muscle, rather than defaulting to translating from English.

My goal was to build something that is fast, relatively inexpensive, and not prone to misleading people. After some experimentation, I found that pairing GPT-3.5 with Microsoft machine translation works great! I'm using GPT-3.5 to generate an English version of the input, then Microsoft machine translation to translate the English version into Chinese. I've written a blog post about how I arrived at this approach: https://maybecoding.bearblog.dev/my-attempt-at-an-ai-writing...

The tool is pretty basic from a technical standpoint. There's a PHP backend that handles the API calls to OpenAI and Microsoft. The frontend is plain HTML with a bit of JS for interactivity - but the whole thing works fine without JS.

Hopefully other folks find this useful too. I'm interested to know whether I could have approached this problem in a different/better way. Thanks!

Show HN: My AI writing assistant for Chinese
unscrambler.dpw.me

Re: Show HN: My AI writing assistant for Chinese

#2
Oh thanks for sharing. This seems super useful. It's been a long time since I learned some Chinese but this would have been very useful when I was learning Chinese.

Quite often I find myself in that situation where I know most of a sentence but not how to put together.

Re: Show HN: My AI writing assistant for Chinese

#3

Oh thanks for sharing. This seems super useful. It's been a long time since I learned some Chinese but this would have been very useful when I was learning Chinese. Quite often I find myself in that situation where I know most of a sentence but not how to put together.

Thanks for the kind words!

I’ve found it very helpful for staying in the zone and getting better at “thinking” in Chinese

If you start learning Chinese again in the future, I hope you find it useful too!

Re: Show HN: My AI writing assistant for Chinese

#4
When I was testing the language capacities of LLM, Claude 2 was the only one to speak Georgian almost at a native level, better than Google translate and way better than GPT-4 (GPT-3.5 was just gibberish).

I'm curious if Claude models (now the version 3 has been released) work really well with Chinese too (beyond Microsoft Translator). Also there are several good open source bilingual models like Qwen.

Re: Show HN: My AI writing assistant for Chinese

#5
post #4

When I was testing the language capacities of LLM, Claude 2 was the only one to speak Georgian almost at a native level, better than Google translate and way better than GPT-4 (GPT-3.5 was just gibberish). I'm curious if Claude models (now the version 3 has been released) work really well with Chinese too (beyond Microsoft Translator). Also there are several good open source bilingual models like Qwen.

I’ll check out those models - thank you!

According to my wife (a Chinese native speaker), GPT-3.5 is bad at outputting Chinese but GPT-4 does a good job

Re: Show HN: My AI writing assistant for Chinese

#8
I’m just starting to learn Mandarin at the moment and I’ve found LLMs useful for this. I can ask the question “I’m learning Mandarin, can you break this sentence into individual hanzi and explain it?” and it will do a good job of explaining everything. Or I can say something like “I was transcribing an audio recording for an exercise and I wrote X but the answer was Y, what did I do wrong?” and it will tell me that I misheard 妈 (ma, the question particle) as 马 (mǎ, which means “horse”) etc. Or I can paste in a sentence and ask it if it’s grammatically correct, and it will explain what I did wrong and how to correct it.

For instance:

> > I’m learning Mandarin, can you break this sentence into individual hanzi and explain it? 果汁很好喝

> Certainly! Let's break down the sentence "果汁很好喝" into individual hanzi (Chinese characters) and explain what each character and the whole sentence mean.

> - 果 (guǒ) - Fruit

> - 汁 (zhī) - Juice

> - 很 (hěn) - Very; quite

> - 好 (hǎo) - Good

> - 喝 (hē) - to drink

> So, when you put these characters together:

> - 果汁 (guǒ zhī) means "fruit juice."

> - 很 (hěn) is an adverb that intensifies the adjective that follows. When used before an adjective, it indicates a high degree of something, commonly translated as "very" or "quite" in English.

> - 好喝 (hǎo hē) combines "good" (好 hǎo) and "to drink" (喝 hē), which together mean "tasty" or "good to drink."

> So, the sentence 果汁很好喝 translates to "The fruit juice is very tasty" or more directly, "Fruit juice is very good to drink." It's a simple sentence structure expressing that the speaker finds the fruit juice to be quite delicious.

It does idioms too:

> > I’m learning Mandarin, can you break this sentence into individual hanzi and explain it? 吃醋

> Sure, I can help with that. The sentence "吃醋" consists of two characters: "吃" and "醋".

> - 吃 (chī): This character means "to eat" or "to consume".

> - 醋 (cù): This character means "vinegar".

> However, when put together as "吃醋", the phrase doesn't literally mean "eat vinegar". In Chinese, "吃醋" is an idiomatic expression that means to be jealous or envious, usually in the context of a romantic relationship. It can be translated to feeling "sour" over someone's interaction with others, hence the metaphor of "eating vinegar". This phrase showcases how Mandarin often uses vivid imagery to encapsulate emotions and situations.

Even going down to a locally running Mistral 7b gives pretty good results, although it sometimes makes minor mistakes or doesn’t give as thorough an explanation as the larger models. Still very useful for my stage though, where I’m mostly just trying to remember something that isn’t quite fully memorised yet, or exploring what’s adjacent to my current knowledge.

Re: Show HN: My AI writing assistant for Chinese

#10

I’m just starting to learn Mandarin at the moment and I’ve found LLMs useful for this. I can ask the question “I’m learning Mandarin, can you break this sentence into individual hanzi and explain it?” and it will do a good job of explaining everything. Or I can say something like “I was transcribing an audio recording for an exercise and I wrote X but the answer was Y, what did I do wrong?” and it will tell me that I…

If you're looking for a local translation tool, I wrote a small CC-CEDICT lookup script in shell+JS then eventually rewrote it in Go so I could run it on whatever computer I was using at the time: https://github.com/alisonatwork/cedict

It just does a dumb greedy search to try find the longest chain of characters for the translation, but that turns out to work more often than not:

  $ cedict -m 果汁很好喝
  果汁    [guǒ zhī]       /fruit juice/
  很      [hěn]   /(adverb of degree)/quite/very/awfully/
  好喝    [hǎo hē]        /tasty (drinks)/
I wanted to add different strategies on -s like dict(1), but I never got round to it because it was easy enough to just force breaking the word by adding spaces:

  $ cedict -m 入鄉隨俗
  入乡随俗        [rù xiāng suí sú]       /When you enter a village, follow the local customs (idiom); do as the natives do/When in Rome, do as the Romans do/
  $ cedict -m 入鄉 隨俗
  入      [rù]    /to enter/to go into/to join/to become a member of/to confirm or agree with/abbr. for 入聲|入声[rù shēng]/
  乡      [xiāng] /country or countryside/native place/home village or town/township (PRC administrative unit)/
  随俗    [suí sú]        /according to custom/to do as local custom requires/do as the Romans do/ 
Now I live in Taiwan it might be neat to update it to output traditional characters, but to be honest I think simplified is easier to read and learn for foriegners.
Post reply on HN