search

earlyprint / earlyprint.github.io

Homepage for the EarlyPrint Project: Curating and Exploring Early Printed English
https://earlyprint.org/
2 stars 2 forks source link

Adorn named entities in TEI texts. #12

Open pibburns opened 4 years ago

pibburns commented 4 years ago

We should consider adorning named entities in the TEI texts.

Pib wrote preliminary code to do this several years ago for Sylvester Johnson's Purchas project. We could extend that, or write/use something different.

In tandem we will also want to consider linking names to authoritative sources as well as disambiguating names.

jrladd commented 4 years ago

Pib sent me some of this code, which I am planning to look over and even try out. I've done some work on named entities in the past (and I'll be talking about some of it at the upcoming Sixteenth Century conference).

As we all know, name reconciliation is an even harder task than name recognition, but it's here that some of the methods we used for Six Degrees might be adapted to our purposes. This is a very big prospective project, but it's something we can think about in the long term.