RST Discourse Parser for Russian: An Experimental Study of Deep Learning Models

Authors

Smirnoff I. Chistova E. Kobozeva M.

Annotation

This work presents the first fully-fledged discourse parser for Russian based on the Rhetorical Structure Theory of Mann and Thompson (1988). For the segmentation, discourse tree construction, and discourse relation classification we employ deep learning models. With the help of multiple word embedding techniques, the new state of the art for discourse segmentation of Russian texts is achieved. We found that the neural classifiers using contextual word representations outperform previously proposed feature-based models for discourse relation classification. By ensembling both methods, we are able to further improve the performance of the discourse relation classification achieving the new state of the art for Russian.

External links

DOI: 10.1007/978-3-030-72610-2_8

ResearchGate: https://www.researchgate.net/publication/350745602_RST_Discourse_Parser_for_Russian_An_Experimental_Study_of_Deep_Learning_Models

Watch presentation by Elena Chistova at the AIST conference official channel:

Reference link

Chistova E., Shelmanov A., Pisarevskaya D., Kobozeva M., Isakov V., Panchenko A., Toldova S., Smirnov I. RST Discourse Parser for Russian: An Experimental Study of Deep Learning Models // International Conference on Analysis of Images, Social Networks and Texts. — Lecture Notes in Computer Science, vol 12602, Springer, Cham, 2021, pp. 105-119.