Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings

1 code implementation • 9 Jul 2018 • Nikola Ljubešić, Darja Fišer, Anita Peti-Stantić

We show that the notions of concreteness and imageability are highly predictable both within and across languages, with a moderate loss of up to 20% in correlation when predicting across languages.

Cross-Lingual Transfer Word Embeddings