VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment
This work addresses the scalability and efficiency limitations of state-of-the-art ontology alignment systems, which often rely on domain-dependent approaches, benefiting researchers and practitioners in data integration and related fields.
This paper introduces VeeAlign, a deep learning model that employs a dual-attention mechanism to create contextualized representations of concepts for ontology alignment. The model is designed to be flexible and scalable across different domains and languages, leveraging both syntactic and semantic information. It was evaluated on four diverse datasets, demonstrating superior performance.
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.