Identification of generic name-derived semantic relationships of geographical entities

When translating the names of geographical entities, it is often necessary to adopt specific translation strategies for geographical names that have a general name derivation relationship with other geographical names. Traditional rule-based methods are insufficient for identifying widespread generic name derivation relationships between geographical entities. This paper proposes a method for identifying general name derivation relationships based on prompt learning and Semantic-Spatial Distribution Attention Feature Fusion (SSD-AFF) to address this issue. This method aims to improve the efficiency and accuracy of identifying general name derivation relationships between place names. This method is divided into two steps: 1) Identification of derived place names. We use prompt learning methods, where the generic name derivation pattern serves as the context for place names, allowing a bidirectional language model to classify the place names. 2) Identification of derivation relationships. We utilize a Semantic-Spatial Distribution Feature Fusion module (SSD-AFF) to integrate various features of generic name derivation relationships, thereby achieving the identification of such relationships between place names. Experiments show that this method outperforms traditional methods in terms of performance and robustness and has certain application value in bilingual map production.