Automatic Mining of Discourse Connectives for Russian

Toldova, Svetlana; Kobozeva, Maria; Pisarevskaya, Dina

doi:10.1007/978-3-030-01204-5_8

Search citation statements

Order By: Relevance

Paper Sections

Select...

Features1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

Publication Types

Select...

Other1

Book1

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic features include averaged word embeddings of each DU. The word embedding model used in this work is described in (Toldova et al, 2018). The peculiarity of this model is that stop words and punctuation marks were not removed during pretraining, whereby discourse connectives were not lost.…”

Section: Featuresmentioning

confidence: 99%

Towards the Data-driven System for Rhetorical Parsing of

Shelmanov¹,

Pisarevskaya²,

Chistova³

et al. 2019

Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019

Self Cite

View full text Add to dashboard Cite

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 F 1 = 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.

show abstract

Section: Featuresmentioning

confidence: 99%