Semantic role labeling with neural networks for texts in Russian

A. O. Shelmanov, D. A. Devyatkin

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)


We present and evaluate neural network models for semantic role labeling of texts in Russian. The benchmark for evaluation and training was prepared on the basis of the FrameBank corpus. The paper addresses different aspects of learning a neural network model for semantic role labeling on different feature sets including syntactic features acquired with the help of SyntaxNet. In this work, we rely on architecture engineering and atomic features instead of commonly used feature engineering. We investigate the ability of learning a model for labeling arguments of "unknown" predicates that are not present in a training set using word embeddings as features for the replacement of predicate lemmas. We publish the prepared benchmark and the models. The experimental results can be used as a baseline for further research in semantic role labeling of texts in Russian.

Original languageEnglish
Pages (from-to)245-256
Number of pages12
JournalKomp'juternaja Lingvistika i Intellektual'nye Tehnologii
Issue number16
Publication statusPublished - 2017
Externally publishedYes


  • Deep learning
  • Frame parsing
  • Neural network
  • Semantic parsing
  • Semantic role labeling
  • Word embeddings


Dive into the research topics of 'Semantic role labeling with neural networks for texts in Russian'. Together they form a unique fingerprint.

Cite this