Classification Models for RST Discourse Parsing of Texts In Russian

Authors

Smirnoff I. Chistova E. Kobozeva M.

Annotation

The paper considers the task of automatic discourse parsing of texts in Russian. Discourse parsing is a well-known approach to capturing text semantics across boundaries of single sentences. Discourse annotation was found to be useful for various tasks including summarization, sentiment analysis, question-answering. Recently, the release of manually annotated Ru-RSTreebank corpus unlocked the possibility of leveraging supervised machine learning techniques for creating such parsers for Russian language. The corpus provides the discourse annotation in a widely adopted formalisation – Rhetorical Structure Theory. In this work, we develop feature sets for rhetorical relation classification in Russian-language texts, investigate importance of various types of features, and report results of the first experimental evaluation of machine learning models trained on Ru-RSTreebank corpus. We consider various machine learning methods including gradient boosting, neural network, and ensembling of several models by soft voting.

External links

PDF at the Dialogue international conference website: www.dialog-21.ru/media/4595/chistovaevplusetal-076.pdf

PDF at the Higher School of Economics website: https://www.hse.ru/data/2019/06/20/1488855652/2019_Dialogue_Chistova.pdf

eLIBRARY: https://elibrary.ru/item.asp?id=43244096

RUDN University. Repository: https://repository.rudn.ru/en/records/article/record/65814/

Semantic Scholar: https://api.semanticscholar.org/CorpusID:199483550

Reference link

Chistova E. V., Shelmanov A. O., Kobozeva M. V., Pisarevskaya D. B., Smirnov I. V., Toldova S. Yu. Classification Models for RST Discourse Parsing of Texts In Russian // Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2019”. – 2019. – Pages 163-176.