# Automated Word Stress Detection in Russian

## TL;DR

This paper presents a method for automated word stress detection in Russian using character-level bidirectional RNNs, achieving over 90% accuracy without relying on part-speech tags, and highlights the importance of annotated corpora for training.

## Contribution

The study introduces a simple bidirectional RNN approach for Russian word stress detection that outperforms dictionary-based methods by leveraging annotated corpora.

## Key findings

- Achieved over 90% accuracy in stress detection.
- Annotated corpus training is more effective than dictionary-based training.
- Character-level RNNs effectively model Russian word stress patterns.

## Abstract

In this study we address the problem of automated word stress detection in Russian using character level models and no part-speech-taggers. We use a simple bidirectional RNN with LSTM nodes and achieve the accuracy of 90% or higher. We experiment with two training datasets and show that using the data from an annotated corpus is much more efficient than using a dictionary, since it allows us to take into account word frequencies and the morphological context of the word.