Evaluation of Morphological Embeddings for the Russian Language
This work addresses the evaluation of morphological embeddings for Russian, an understudied morphologically rich language, but the results are incremental as they show no improvement over existing methods.
The paper investigated whether incorporating morphology into word embeddings improves performance on downstream NLP tasks for the morphologically rich Russian language, finding that morphology-based embeddings did not outperform FastText and were significantly outperformed by BERT.
A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that morphology-based embeddings trained with Skipgram objective do not outperform existing embedding model -- FastText. Moreover, a more complex, but morphology unaware model, BERT, allows to achieve significantly greater performance on the tasks that presumably require understanding of a word's morphology.