Char-RNN for Word Stress Detection in East Slavic Languages

TL;DR

This paper investigates the use of recurrent neural networks for word stress detection in East Slavic languages, introducing new datasets and demonstrating cross-lingual transfer learning to improve accuracy.

Contribution

It presents new annotated datasets for Russian, Ukrainian, and Belarusian, and explores cross-lingual transfer learning with RNNs for resource-poor language stress detection.

Findings

Cross-lingual models outperform monolingual ones.

Additional languages improve stress detection accuracy.

Transfer learning is effective for resource-poor languages.

Abstract

We explore how well a sequence labeling approach, namely, recurrent neural network, is suited for the task of resource-poor and POS tagging free word stress detection in the Russian, Ukranian, Belarusian languages. We present new datasets, annotated with the word stress, for the three languages and compare several RNN models trained on three languages and explore possible applications of the transfer learning for the task. We show that it is possible to train a model in a cross-lingual setting and that using additional languages improves the quality of the results.