Abstract
We present the Supervised Directional Similarity Network (SDSN), a novelneural architecture for learning task-specific transformation functions on topof general-purpose word embeddings. Relying on only a limited amount ofsupervision from task-specific scores on a subset of the vocabulary, ourarchitecture is able to generalise and transform a general-purposedistributional vector space to model the relation of lexical entailment.Experiments show excellent performance on scoring graded lexical entailment,raising the state-of-the-art on the HyperLex dataset by approximately 25%.