Towards a Dependency Parser for Greek Using a Small Training Data Set
Jesús Herrera, Pablo Gervás · Redalyc (Universidad Autónoma del Estado de México) · 2008
"Some experiments have been accomplished in order to determine strate- gies that should be followed to build a small corpus capable to train accurately a dependency parser for Greek, using a Machine Learning tool. Thus, several prob- lems that should be treated such syntactic coverage, e ff ect of word order or e ff ect of morphology in languages with syntactic roles expressed morphologically, are em- pirically studied. With the results presented we would like to lay the foundations for a systematic and e ff ective way to develop dependency parsers when lacking huge training corpora. The ideas outlined could be used not only for Greek but for other languages. Keyword"