Sign Clustering and Topic Extraction in Proto-Elamite
TL
TL;DR
This first attempt at using techniques from computational linguistics to analyze the undeciphered proto-Elamite script using hierarchical clustering, n-gram frequencies, and LDA topic models demonstrates the utility of these techniques as an aid to manual decipherment.
Abstract
We describe a first attempt at using techniques from computational linguistics to analyze the undeciphered proto-Elamite script. Using hierarchical clustering, n-gram frequencies, and LDA topic models, we both replicate results obtained by manual decipherment and reveal previously-unobserved relationships between signs. This demonstrates the utility of these techniques as an aid to manual decipherment.
References33 items
1
Measuring LDA topic stability from clusters of replicated runs
2
Machine Translation and Automated Analysis of the Sumerian Language
3
Decoding Anagrammed Texts Written in an Unknown Language and Script
4
Generalised Brown Clustering and Roll-Up Feature Generation
5