“…Employing machine learning and a set of features representing sentences, the goal is to discard sentences that are not part (or do not contain a component) of an argument. As reported also by Lippi and Torroni (2015a), the vast majority of existing approaches employ "classic, off-the-self" classifiers, while most of the effort is devoted to highly engineered features. A plethora of learning algorithms have been applied on the task, including Naive Bayes (Moens et al, 2007;Park and Cardie, 2014), Support Vector Machines (SVM) (Mochales and Moens, 2011;Rooney et al, 2012;Park and Cardie, 2014;Stab and Gurevych, 2014b;Lippi and Torroni, 2015b), Maximum Entropy (Mochales and Moens, 2011), Logistic Regression (Goudas et al, 2014(Goudas et al, , 2015Levy et al, 2014), Decision Trees and Random Forests (Goudas et al, 2014(Goudas et al, , 2015Stab and Gurevych, 2014b).…”