Towards the Data-driven System for Rhetorical Parsing of Russian Texts
Results of the first experimental evaluation of machine learning models trained on Ru-RSTreebank {--} first Russian corpus annotated within RST framework {--} are presented. Various lexical, quantitative, morphological, and semantic features were used. In rhetorical relation classification, ensemble of CatBoost model with selected features and a linear SVM model provides the best score (macro F1 = 54.67 {\mbox{$\pm$}} 0.38). We discover that most of the important features for rhetorical relation classification are related to discourse connectives derived from the connectives lexicon for Russian and from other sources.
PDF Abstract