Euskarazko ezeztapenaren tratamendu automatikorakoazterketa
- Begoña Altuna Diaz
- Maxux Aranzabe Urruzola
- Arantza Diaz de Ilarraza Sanchez
- Iñaki Alegria (ed. lit.)
- Ainhoa Latatu (ed. lit.)
- Miren Josu Omaetxebarria (ed. lit.)
- Patxi Salaberri (ed. lit.)
Publisher: Udako Euskal Unibertsitatea, UEU = Universidad Vasca de Verano
ISBN: 978-84-8438-627-8, 978-84-8438-628-5
Year of publication: 2017
Volume Title: Giza Zientziak eta Artea
Tome: 1
Volume: 1
Pages: 127-134
Congress: Ikergazte. Nazioarteko Ikerketa Euskaraz (2. 2017. Iruñea)
Type: Conference paper
Abstract
Natural language processing aims to the information extraction and analysis. In this paper, we presentthe analysis and annotation of negation in Basque, as a complement to the temporal informationprocessing, since negation affects event factuality resolution and event role definition. We have analysedthe background and we have studied how negation is expressed in Basque and we have normalisedthat information. In order to evaluate the normalisation scheme and to create a corpus for machine learning, we have conducted a manual annotation experiment. Based on the experiment results,we have analysed the errors to measure the difficulty of the task and to improve the annotation guidelines.