The Dictionary's Next Evolution
During the time I lived in Germany, figuring out how to pick up the language was a priority. If not for personal reasons, administrative ones (otherwise there was no way I was getting a refund from the Deutsche Bahn).
I came in expecting German to be about as hard as French, but hindsight makes this look naive. The case system in German makes French seem breezy. That said, it's not really a fair comparison. French got a year of my attention full-time, surrounded by professors. And although I'm sure it would have been as fun doing the same with German, that just wasn't on the table this year. So, this puts me in a situation driven by practical limitations. Enter Large Language Models.
I cannot strongly enough endorse my experience using AI as a translation partner instead of a translation tool. I'm depending on it to coach me. This also brushes against a funny topic that people really involved with language learning seem to have a strong opinion on: which translation app to use. Google Translate is for shame (unless you've got C2 and your hot take is that it's fine), DeepL does more reliable translating, and WordReference has good etymologies and other context. But what I've been doing with AI has been so far away from anything these services are offering.
With the "Projects" feature, where you can define certain instructions as context for every message, I have been getting a much wider understanding for the appropriateness of when to use one phrase over another. And this is the problem of learning another language.
What's more, this approach centers real situations instead contrived worksheet examples. (If DuoLingo asks me how big the elephant is one more time, I'm gonna lose it).Writing emails to the people I work with (in this case, administrators at the University of Bonn) has been a perfect opportunity for this! I have the time to sit and focus on what I want to say and how to get that phrasing right in a way which not only communicates my meaning but also fits the social norms of sending emails in German. More than conjugating for the right level of formality, I also want to get little details like choosing the right greetings and sign-offs, putting my commas in the right places, and use capitalization appropriately (hint: it's not the same as in America).
To do these things, I've given ChatGPT the following instructions:
Never use the internet.
Context: I am an English and French speaker living in Germany and learning German.
Follow these instructions strictly:
- Always answer concisely and clearly. Do not add comments or filler content.
- If given a phrase in English (without additional context), translate it into simple, natural German—not a literal word-for-word translation. Prioritize core meaning, common phrasing, and basic vocabulary and conjugations (A1-A2 level).
- After providing the German translation: a. Then, provide an idiomatic French translation (natural phrasing, not word-for-word). b. Repeat the German sentence a second time, but this time following any German words that would be hard for an A1 student with their English equivalents in brackets [like this].
- Provide a list of those German words you determined were difficult, including their IPA spelling. Make the IPA spelling a clickable link for the DeepL translation using the pattern: https://www.deepl.com/translator#de/en/QUERY_WORD
- Do not label any of the three outputs. Present them consecutively without headings or extra commentary.
- If given the keyword "formal" or "informal/casual/friendly", conjugate accordingly.
- If I give you just one word in German, I want you to give that back to me spelled using the IPA.
These rules are tailored to me, but I think they represent a good starting off point for anyone looking to use LLMs to help them learn a new language. For example, with the 3rd rule, I lean on my French to help me quickly assess if the German is being conjugated formally or informally, but this could definitely be adapted to English with a parenthetical indicating the level of formality the writing is using.
Using this collaborative approach with AI has really taken me beyond translation. Even though DeepL is best in class for most translations, it does nothing for all the times when I'm wondering why a certain word was used or whether there were rephrasings which could better convey my intended meaning. AI as a translation-partner instead of a tool has done just that for me, and maybe it can for you too.
