D4.1.1 Whitepaper on DaMSym

This whitepaper describes the reasoning and possible exploitation of DaMSym, intended as a software platform that performs several functions on ancient text corpora specifically prepared: 1) setup of the various corpora for the WP4 studied languages 2) PoS tagging techniques 3) word embedding extraction 4) document understanding through comparison with corpora 5) properties visualisation. Each function is detailed separately, but the whitepaper also describes DaMSym in its entirety, as a single platform for performing all the above tasks in subsequent phases. BEFORE the revision: This whitepaper describes the reasoning and possible exploitation of DaMSym, intended as a software that performs several functions: 1) word embedding extraction 2) machine translation 3) text classification and document understanding 4) standoff properties annotation 5) properties visualisation. Each function is detailed separately, but the whitepaper also describes DaMSym in its entirety, as a single platform for performing all the above tasks in subsequent phases.