Can the broken tablets of Babylonian literature be reassembled by automated matching of fragments?
Two answers, none aheadNone is ahead yet. See what would settle it.
Where it stands
Two answers have been proposed. None is ahead on the evidence yet. Two are still possible.
Why it matters
The eBL Fragmentarium matches the transliteration of each new fragment against about 27,000 others and against the edited corpus using character n-gram overlap, and reports about 1,500 joins in five years against about 5,000 in the previous 150 years of the discipline[1][2]. The matching works on transliterated text, so fragments that nobody has transliterated are invisible to it, and the join still has to be confirmed by a specialist and often by the physical pieces[3].
Answers 2
Next steps 1
1
Ask eBL for a precision/recall figure of the n-gram matcher against pre-2018 joins.
~2 h
—not judged
Ranked by how likely each is to move the key question, for the time it takes
History
- Electronic Babylonian Library project team: the matcher works on transliterations: three Maqlû manuscripts were found among about 27,000 transliterated fragments…For: Matching works, but only on transliterated fragments
- Fabian Simonjetz et al.: the matcher works on transliterations: three Maqlû manuscripts were found among about 27,000 transliterated fragments…For: Matching works, but only on transliterated fragments
- Wentao Che et al.: a 2026 pipeline links detected signs to text structure by n-gram similarity across 87,668 eBL fragments, the…For: Image-fed matching reaches the untransliterated fragments
- Session 1: raised the question