Robust Handling of Polysemy via Sparse Representations

• DOI: 10.48550/arxiv.1805.07398
• Publication Date: 2018-01-01
• Authors: Abhijit Mahabal; Dan Roth; Sid Mittal
• Keywords: Polysemy; Word2vec; Representation

Words are polysemous and multi-faceted, with many shades of meanings. We suggest that sparse distributed representations more suitable than other, commonly used, (dense) to express these multiple facets, present Category Builder, a working system that, as we show, makes use support multi-faceted lexical representations. argue the set expansion task is well suited study meaning distinctions since word may belong sets different reason for membership in each. therefore exhibit performance Builder on this task, while showing our representation captures at same time analogy problems such "the Ganga Egypt" or Voldemort Tolkien". shown be expressive outperform dense Word2Vec some classes despite being only two three input terms.