Engine

This page documents conventions, standards and relevant workflows used for the annotation of our corpus data with the help of the Giellatekno toolkit, specifically an annotation engine incl. preprocessing-tokenizing, morphological analysis and disambiguation.

Intro

FST is…

Workflows

ELAN-->FST-->ELAN

Scripts

• sending ELAN-data to the analyzer
• sending analyzed data back into ELAN
• creating new tiers and annotations on them based to search results on higher level tier