New AI translates 5,000-year-old cuneiform tablets instantly

bigthink.com New AI translates 5,000-year-old cuneiform tablets instantly

Thousands of ancient cuneiform tablets remain untranslated. A team of researchers have developed an AI to unlock their secrets.

Researchers have unearthed hundreds of thousands of cuneiform tablets, but many remain untranslated. Translating an ancient language is a time-intensive process, and only a few hundred experts are qualified to perform it. A recent study describes a new AI that produces high-quality translations of ancient texts.

19 comments

@AutoTLDR
- TL;DR: (AI-generated 🤖)
  A team of archaeologists and computer scientists has developed an artificial intelligence (AI) model that can translate ancient Akkadian cuneiform, a language from 5,000 years ago. Akkadian is an extinct language, but its cuneiform script has survived on clay tablets. Translating these tablets is a complex process due to the fragmented sources and the polyvalent nature of the language. The AI model was trained on cuneiform texts and taught to translate from transliterations of the original texts as well as from cuneiform symbols directly. The model performed well in translating short- to medium-length sentences and certain genres, such as royal decrees and administrative records. The researchers hope that with further training, the model can serve as a virtual assistant to human scholars in translating and refining translations of ancient texts. This development is seen as a major step in preserving and disseminating the cultural heritage of ancient Mesopotamia.
  
  Good bot

It just randomly generated some believable bullshit, as usual.
- It’s pretty freaking great at stuff like that though. We use a custom programming language at work, there are similarities with Haskell and others, but also many differences.
  We had a little game where a colleague had put together some team-exercises. He had encrypted a message in base64 and therein written instructions for code, in our custom language that when run gave you an output.
  ChatGPT managed to print out the, 100% non random output, and 100% stuff that’s never been anywhere on the internet, without trouble.
  
  Google’s DeepMind was able to teach itself Indonesian without being directly trained on how to do so. Ancient Sumerian doesn’t seem too far fetched, all things considered!
  
  Google’s DeepMind was able to teach itself Indonesian without being directly trained on how to do so. Ancient Sumerian doesn’t seem too far fetched, all things considered!
  
  I can’t even wrap my head around how a large language model can do this.
  
  That's the problem, you see.. it is great for simple things. Then you start believing in it and give more complicated tasks. It will fail, you will never know until it is too late. We are doomed....

Impressive. I can't even translate what I wrote 10 minutes ago.
- Woah look at Fancy Lasagna over here with 10 whole minutes of memory
  
  It ain't much but it's honest work.

So this is not LLM?
- Seems like it isn’t:
  the same technology under the hood of Google Translate

19 comments