<ul><li>Taxonomy Expansion can be formulated as a set representation learning task using fuzzy sets.</li><li>Existing works model sets as vectors or geometric objects, which are not closed under set operations.</li><li>FUSE (Fuzzy Set Embedding) is a new formulation that approximates set representation as a fuzzy set, preserving information efficiently.</li><li>Empirical results show FUSE achieves up to 23% improvement in taxonomy expansion compared to existing baselines.</li></ul>

FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion

Discover more