NLP-enabled string matching. I wish there were more details about _how_ they did it in the NYT article since that would be much more interesting than just saying "AI".
The comments here are really atrocious and ironically all seem LLM-generated.
This seems to be like kakasi for Japanese in that Japanese writing system does not separate words by spaces and one kanji can be read in multiple ways. As I understand the same is also true for cuneiform and this is an attempt to solve it.
A generative model makes no sense for this application. I think they are using the machines to surface possible matches for humans to consider, similar to the use of RNNs for potential drug candidates.
What an odd saying. To me it reads, "The things that affect my life are my top priority".
I'm pretty sure he means to be talking about people who engage in it for funsies and yet approach it with the same level of importance. But there are those for whom politics is still literally life and death.
24 comments
[ 3.1 ms ] story [ 61.8 ms ] threadReading Akkadian cuneiform using natural language processing (NLP): https://journals.plos.org/plosone/article?id=10.1371/journal...
Thank you!
https://en.m.wikipedia.org/wiki/Codex_Seraphinianus
Old: https://www.ebl.lmu.de/fragmentarium
Related papers:
- https://aclanthology.org/2024.lrec-main.1197.pdf
- https://openreview.net/pdf?id=z6ZGKexu8un
NLP-enabled string matching. I wish there were more details about _how_ they did it in the NYT article since that would be much more interesting than just saying "AI".
The comments here are really atrocious and ironically all seem LLM-generated.
I'm pretty sure he means to be talking about people who engage in it for funsies and yet approach it with the same level of importance. But there are those for whom politics is still literally life and death.