Embedding Words and Senses Together via Joint Knowledge-Enhanced Training

Word embeddings based on neural networks are widely used in Natural Language Processing. However, despite their success in capturing semantic information from massive corpora, word embeddings still conflate different meanings of a word into a single vectorial representation and do not benefit from information available in lexical resources. We address this issue by proposing a new model that jointly learns word and sense embeddings and represents them in a unified vector space by exploiting large corpora and knowledge obtained from semantic networks. We evaluate the main features of our approach qualitatively and quantitatively in various tasks, highlighting the advantages of the proposed method with respect to state-of-the-art wordand sense-