LG at WiC-ITA: Exploring the relation between semantic distance and equivalence in translation

The Word in Context task has been addressed here on the basis of a simple intuition: if the same lemma has different senses in two different contexts, it tends to be translated (in other languages) with two different lemmas; conversely, in the case of the same sense, translation lemmas tend to be the same. The proposed methodology is based on the translation of sentence pairs in 21 languages, and the use of a SVM classifier/regressor. Obtained results are excellent in binary classification and average in regression tasks.