Joint Embeddings of Hierarchical Categories and Entities
This work addresses the limitation in knowledge representation for AI systems by enabling better semantic understanding through hierarchical category embeddings, though it appears incremental as it builds on existing embedding techniques.
The paper tackled the problem of learning distributed representations for categories without incorporating hierarchical structures, proposing a framework that embeds entities and categories into a semantic space using knowledge bases and taxonomy hierarchies, resulting in superior performance in concept categorization and semantic relatedness compared to previous state-of-the-art methods.
Due to the lack of structured knowledge applied in learning distributed representation of categories, existing work cannot incorporate category hierarchies into entity information.~We propose a framework that embeds entities and categories into a semantic space by integrating structured knowledge and taxonomy hierarchy from large knowledge bases. The framework allows to compute meaningful semantic relatedness between entities and categories.~Compared with the previous state of the art, our framework can handle both single-word concepts and multiple-word concepts with superior performance in concept categorization and semantic relatedness.