Evaluation of Greek Word Embeddings
This work addresses the lack of evaluation resources for Greek word embeddings, which is important for NLP applications in Greek, though it is incremental as it adapts existing English methods.
The paper tackled the problem of evaluating word embeddings for the Greek language by creating new analogy and similarity corpora adapted from English benchmarks, testing seven models, and finding that meaningful representations could be generated while noting that morphological complexity and polysemy affect quality.
Since word embeddings have been the most popular input for many NLP tasks, evaluating their quality is of critical importance. Most research efforts are focusing on English word embeddings. This paper addresses the problem of constructing and evaluating such models for the Greek language. We created a new word analogy corpus considering the original English Word2vec word analogy corpus and some specific linguistic aspects of the Greek language as well. Moreover, we created a Greek version of WordSim353 corpora for a basic evaluation of word similarities. We tested seven word vector models and our evaluation showed that we are able to create meaningful representations. Last, we discovered that the morphological complexity of the Greek language and polysemy can influence the quality of the resulting word embeddings.