VeeAlign:基于双注意力的多面上下文表示
VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment
摘要:
本体对齐是一个重要的研究问题,适用于各种领域,如数据集成,数据传输,数据准备,等国家的最先进的(SOTA)本体对齐系统通常使用天真的领域相关的方法与手工制作的规则或特定领域的架构,使他们不可扩展和效率低下。在这项工作中,我们提出了VeeAlign,这是一种基于深度学习的模型,它使用一种新的双注意力机制来计算概念的上下文表示,然后再用来发现对齐。通过这样做,我们的方法不仅能够利用编码在本体中的语法和语义信息,它也是,通过设计,灵活和可扩展到不同的领域,以最小的努力。我们在来自不同领域和语言的四个不同数据集上评估了我们的模型,并通过这些结果以及详细的消融研究建立了它的优越性。使用的代码和数据集可在https://github.com/Remorax/VeeAlign上获得。
英文摘要:
Ontology Alignment is an important research problem applied to various fields such as data integration, data transfer, data preparation, etc. State-of-the-art (SOTA) Ontology Alignment systems typically use naive domain-dependent approaches with handcrafted rules or domain-specific architectures, making them unscalable and inefficient. In this work, we propose VeeAlign, a Deep Learning based model that uses a novel dual-attention mechanism to compute the contextualized representation of a concept which, in turn, is used to discover alignments. By doing this, not only is our approach able to exploit both syntactic and semantic information encoded in ontologies, it is also, by design, flexible and scalable to different domains with minimal effort. We evaluate our model on four different datasets from different domains and languages, and establish its superiority through these results as well as detailed ablation studies. The code and datasets used are available at https://github.com/Remorax/VeeAlign.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。