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 ± 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 на сайте Association for Computational Linguistics (англ.): https://www.aclweb.org/anthology/W19-2711.pdf
PDF в цифровом архиве ACL Anthology (англ.): https://aclanthology.org/W19-2711.pdf
Shelmanov A., Kobozeva M et al. Towards the Data-driven System for Rhetorical Parsing of Russian Texts // Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019. – 2019. – Pp. 82-87.