Piecing together the epic of Gilgamesh with NLP

<a href="https:&#x2F;&#x2F;archive.ph&#x2F;1uyq7" rel="nofollow">https:&#x2F;&#x2F;archive.ph&#x2F;1uyq7</a>

If you want to skip the journalistic fluffery and go to the technicals here&#x27;s the paper:<p>Reading Akkadian cuneiform using natural language processing (NLP): <a href="https:&#x2F;&#x2F;journals.plos.org&#x2F;plosone&#x2F;article?id=10.1371&#x2F;journal.pone.0240511" rel="nofollow">https:&#x2F;&#x2F;journals.plos.org&#x2F;plosone&#x2F;article?id=10.1371&#x2F;journal...</a>

Id love to see ML take on Codex Seraphinianus. Even if the answers are just hallucinations, they&#x27;d fit thematically.<p><a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Codex_Seraphinianus" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Codex_Seraphinianus</a>

New Fragmentarium Website: <a href="https:&#x2F;&#x2F;fragmentarium.ms&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fragmentarium.ms&#x2F;</a><p>Old: <a href="https:&#x2F;&#x2F;www.ebl.lmu.de&#x2F;fragmentarium" rel="nofollow">https:&#x2F;&#x2F;www.ebl.lmu.de&#x2F;fragmentarium</a><p>Related papers:<p>- <a href="https:&#x2F;&#x2F;aclanthology.org&#x2F;2024.lrec-main.1197.pdf" rel="nofollow">https:&#x2F;&#x2F;aclanthology.org&#x2F;2024.lrec-main.1197.pdf</a><p>- <a href="https:&#x2F;&#x2F;openreview.net&#x2F;pdf?id=z6ZGKexu8un" rel="nofollow">https:&#x2F;&#x2F;openreview.net&#x2F;pdf?id=z6ZGKexu8un</a><p>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 &quot;AI&quot;.<p>The comments here are really atrocious and ironically all seem LLM-generated.

What kind of „AI“ &#x2F; machine learning was used?

<a href="https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20240812222957&#x2F;https:&#x2F;&#x2F;www.nytimes.com&#x2F;2024&#x2F;08&#x2F;12&#x2F;books&#x2F;booksupdate&#x2F;ai-ancient-tablets-gilgamesh.html" rel="nofollow">https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20240812222957&#x2F;https:&#x2F;&#x2F;www.nytim...</a>

[stub for offtopicness. please don&#x27;t.]

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.