Towards the Data-driven System for Rhetorical Parsing of

Artem Shelmanov, Dina Pisarevskaya, Elena Chistova, Svetlana Toldova, Maria Kobozeva, Ivan Smirnov

Abstract

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.
BibTeX
@inproceedings{shelmanov2019towards,
  author = {Artem Shelmanov and Dina Pisarevskaya and Elena Chistova and Svetlana Toldova and Maria Kobozeva and Ivan Smirnov},
  title = {{Towards the Data-driven System for Rhetorical Parsing of}},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2019},
}

Loading related content...

Figure