Binder: Hierarchical Concept Representation through Order Embedding of Binary Vectors

arXiv:2404.10924v1 Announce Type: new
Abstract: For natural language understanding and generation, embedding concepts using an order-based representation is an essential task. Unlike traditional point vector based representation, an order-based representation imposes geometric constraints on the representation vectors for explicitly capturing various semantic relationships that may exist between a pair of concepts. In existing literature, several approaches on order-based embedding have been proposed, mostly focusing on capturing hierarchical relationships; examples include vectors in Euclidean space, complex, Hyperbolic, order, and Box Embedding. …

abstract arxiv binary concept concepts constraints cs.ai cs.cl embedding hierarchical language language understanding natural natural language relationships representation semantic through type understanding vector vectors