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

1 code implementation • WS 2018 • Nikola Ljube{\v{s}}i{\'c}, Darja Fi{\v{s}}er, Anita Peti-Stanti{\'c}

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 Representation Learning +1