Abstract
In this paper, we investigate the relation between negated adjectives and antonyms in English using Distributional Semantics methods. Results show that, on the basis of contexts of use, a negated adjective (e.g., not cold) is typically more similar to the adjective itself (cold) than to its antonym (hot); such effect is less strong for antonyms derived by affixation (e.g., happy - unhappy). © 2018 CEUR-WS. All rights reserved.