Char-RNN for Word Stress Detection in East Slavic 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.

Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects at NAACL-2019

References in corpus (4)

• Sequence to Sequence Learning with Neural Networks
• Massively Multilingual Word Embeddings
• Cross-lingual, Character-Level Neural Morphological Tagging
• SyntaxNet Models for the CoNLL 2017 Shared Task