First Approach to Automatic Text Simplification in Basque

Abstract

Analysis of long sentences are source of problems in advanced applications such as machine translation. With the aim of solving these problems in advanced applications, we have analysed long sentences of two corpora written in Standard Basque in order to make syntactic simplification. The result of this analysis leads us to design a proposal to produce shorter sentences out of long ones. In order to perform this task we present an architecture for a text simplification system based on previously developed general coverage tools (giving them a new utility) and on hand written rules specific for syntactic simplification. Being Basque an agglutinative language this rules are based on morphological features. In this work we focused on specific phenomena like appositions, finite relative clauses and finite temporal clauses. The simplification proposed does not exclude any target audience, and the simplification could be used for both humans and machines. This is the first proposal for Automatic Text simplification and opens a research line for the Basque language in NLP.