| Popis: |
Entity Alignment is a research topic that has drawn a lot of attention from practitioners and researchers from many different areas in the last years. Also referred to as Entity Resolution or Instance Matching, it involves aligning different entity representations that refer to the same real-world entity. However, it is still a challenging solution and existing works are based on iterative methods, blocking schemes and learning approaches. Among these latter, recent works have been using embedding models, focusing only on structural information. In this paper, we present an approach for entity alignment that enrich entity embeddings with different literal information. To be able to express complex relationships between properties and involving multiple entities we employ FrameBase Schema, which is based on linguistic frames to create complex mappings from external knowledge bases to a unique schema. Preliminary experiments showed competitive results to the performance of entity alignment task. |
