Char-RNN for Word Stress Detection in East Slavic Languages
This addresses a resource-poor linguistic problem for East Slavic language processing, but it is incremental as it applies existing RNN methods to new datasets.
The paper tackled word stress detection in Russian, Ukrainian, and Belarusian languages using recurrent neural networks, showing that cross-lingual training improves results, with specific accuracy gains reported (e.g., up to 92% for Russian).
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.