Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
This addresses the issue of polysemy in NLP for applications requiring fine-grained semantic understanding, representing an incremental improvement over existing methods.
The paper tackles the problem of word embeddings conflating multiple meanings into a single vector by proposing a model that learns word and sense embeddings jointly, exploiting large corpora and semantic networks, and shows advantages over state-of-the-art models in various tasks.
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be automatically separated, as it conflates them into a single vector. We address this issue by proposing a new model which learns word and sense embeddings jointly. Our model exploits large corpora and knowledge from semantic networks in order to produce a unified vector space of word and sense embeddings. We evaluate the main features of our approach both qualitatively and quantitatively in a variety of tasks, highlighting the advantages of the proposed method in comparison to state-of-the-art word- and sense-based models.