Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on unseen concepts during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.
翻译:对许多应用而言,分类学是宝贵的资源,但由于人工整理过程昂贵,因此其覆盖面有限,妨碍了其普遍适用性。先前曾试图通过学习将概念嵌入欧洲大陆空间来自动扩大现有分类学,以提高其覆盖面,而分类学本身就具有等级性,更自然地与超双曲线空间的几何特性相一致。在本文中,我们介绍了超Excantan, 这是一种分类学扩展算法,它寻求在一个更显眼的超双曲线嵌入空间中保持分类学结构,并学习代表概念及其与超双曲形神经网络(HGNN)的关系。具体地说,超ExpreExcan利用定位位置嵌入利用现有分类学结构,并描述概念概况信息,以支持在培训期间对隐性概念的推论。实验表明,我们提议的超ExcriExcan 超出基线模型,在Euclidean地貌空间进行代表性学习,并实现在扩展分类学基准方面的最先进的业绩。