New Languages for NLP

Project Goals 

• Use texts and TEI documents to create data 
• Use annotation data to create linguistic data 
• Train new spaCy models using our linguistic data 

cadet

• create new spaCy language object
• create custom language model with pipelines 
• bulk-annotation of  identical tokens and seed terms 
• Able to load TEI documents and their annotations 
• model in the loop 

INCEpTION

• external annotation recommendations 
• built on brat (Berkeley)
• WebAnno 
• Java