Reviews (0)

From PDF to lemmatized text (1)

• Download

This workflow uses the web service stationed in JSI (IJS Slovenia), which is based on Matjaž Juršič's LemmaGen - lemmatization engine. The workflow accepts a PDF file as an input an uses James Eales's wrokflows to preprocess the data. The workflow interactively asks the user of which language is the text, since the lemmatization process is language based. The output is a string in Taverna Workbench.

Created: 2010-09-16 | Last updated: 2012-01-18

Credits: Netr James Eales

Attributions: PDF to plain text Clean plain text