Evaluation of Morphological Embeddings for English and Russian Languages

TL;DR

This study assesses morphology-based embeddings for English and Russian, finding no consistent advantage over standard models like SkipGram and FastText in word similarity and language modeling tasks.

Contribution

It provides a comparative evaluation of morphological embeddings against established baselines, highlighting their comparable performance.

Findings

Morphological embeddings do not outperform SkipGram and FastText.

Performance of morphological embeddings is similar to baseline models.

No stable preference for morphological models was observed.

Abstract

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.