Evaluation of Morphological Embeddings for English and Russian Languages
This work addresses the practical utility of morphological embeddings for NLP researchers, showing incremental results with no clear advantage over existing methods.
The paper evaluated morphology-based word embeddings for English and Russian, finding that they performed no better than baseline models like SkipGram and FastText, with results averaging between the two baselines.
This paper evaluates morphology-based embeddings for English and Russian languages. Despite the interest and introduction of several morphology-based word embedding models in the past and acclaimed performance improvements on word similarity and language modeling tasks, in our experiments, we did not observe any stable preference over two of our baseline models - SkipGram and FastText. The performance exhibited by morphological embeddings is the average of the two baselines mentioned above.