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.
DOI: http://dx.doi.org/10.18653/v1/W19-2711
PDF at the Association for Computational Linguistics website: https://www.aclweb.org/anthology/W19-2711.pdf
PDF at the ACL Anthology archive: https://aclanthology.org/W19-2711.pdf
ResearchGate: https://www.researchgate.net/publication/334600878_Towards_the_Data-driven_System_for_Rhetorical_Parsing_of
Semantic Scholar: https://api.semanticscholar.org/CorpusID:198160784
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.