Using large language models in, you guessed it, language learning

I remember in late 2022, Vibhakar Sarswat told an audience of dozens of developers at a Flutter Stockholm event that he began building his mobile app with the help of GitHub Copilot after finishing a tutorial, and he described GitHub Copilot as “a good teacher.” I chuckled in disbelief.

My early impression of GitHub Copilot was that it was more clumsy than helpful, but it quickly improved and made me more productive. Now in addition to Copilot, I use ChatGPT every day and other gen AI tools quite often too.

Apart from generating code, asking technical questions, making quick queries of syntax and features, I'm using these tools for learning natural languages.

And I find ChatGPT helpful in this very particular way:

ChatGPT converts Chinese characters to Japanese kanjis for me, even when I mistake them for a wrong cognate.

For example, I was trying to read a book about a Japese artist when it mentioend her moving to Berlin. The original sentence was:

ベルリンに拠点を移した

At the time I did not recognize “拠” and thought mistakenly it must be related to 处 (chù).

I tried asking ChatGPT this question:

Explain this sentence to me: ベルリンに 处 点を移した。

Notice I used the wrong character here. The character shown in bold is only used in China.

The sentence “ベルリンに 拠点 を移した” translates to “moved the base to Berlin.”

Here’s a breakdown of the sentence:

• ベルリン (Berurin): Berlin, the capital city of Germany.

• に: A particle indicating the direction or destination of the action, meaning “to” here.

• 拠点 (kyoten): Base or base of operations; it refers to a main location where someone works or operates.

• を移した (wo utsushita): The past form of the verb 移す (utsusu), meaning “to move” or “to transfer.”

So, this sentence indicates that someone or an organization has relocated their main base or operational headquarters to Berlin.

Note how ChatGPT corrected the sentence and converted it to the correct Japanese kanji 拠 (kyo).

Other non-AI dictionary apps would not be able to translate this sentence, break it down, and explain it word by word because 处点 is not a word in either language.

Some dictionary apps might be able to convert correctly if I had written 据点 (jù diăn), the correct equivalent of the same word in Chinese, but if I had known that, I wouldn’t have needed to look it up.