EVA: Unsupervised Entity Linking Using Visual Similarity
EVA uses the visual similarity of entities to create an initial seed dictionary (visual center), providing a completely unsupervised solution. This approach eliminates the need for manual annotation or external knowledge bases.
原文地址: https://www.cveoy.top/t/topic/mYb6 著作权归作者所有。请勿转载和采集!