Applying Estonian Digital Resources and Technologies in a Text Simplification Program
Name
Martin Peedosk
Abstract
The purpose of this Bachelor’s thesis was to research text simplification methods and to create a web-based application to simplify Estonian texts. The web application uses language resources such as the Estonian Wordnet, word2vec model, frequency dictionary, foreign word dictionary and basic vocabulary dictionary, which are used to identify word complexity and suitability to the text.
Graduation Thesis language
Estonian
Graduation Thesis type
Bachelor - Computer Science
Supervisor(s)
Sven Aller,Kadri Vare
Defence year
2017