Automated Word Stress Detection in Russian
This work addresses a domain-specific problem in Russian linguistics, offering an incremental improvement in automated stress detection.
The study tackled automated word stress detection in Russian using character-level models without part-of-speech taggers, achieving over 90% accuracy by leveraging annotated corpus data for better efficiency.
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.