Benchmark data and models for fine-grained geographic NER with few-shot learning

Geographic Named Entity Recognition (GNER) focuses on extracting geographic entity names from text and classifying them into pre-defined categories. Previous methods have not paid much attention to identifying fine-grained categories of geographic entities in sparse data situations, thus remaining limited in serving various geographic applications. To address this limitation, this paper presents a fine-grained GNER task and proposes a fine-grained GNER model, LH-FGNER, which incorporates a prototype network and hierarchical contrastive learning to improve fine-grained GNER. Specifically, the model designs label-guided sentence-level prototypes to capture the contextual semantics of geographic entities. It introduces a hierarchy tree to guide the construction of prototypes in vector space, which utilizes the hierarchy as a priori knowledge to improve the discrimination of fine-grained categories. In addition, two datasets are constructed to support the study of the fine-grained GNER task. Experimental results show that the proposed model is superior to the baseline and is robust. This work provides a methodological reference for few-shot GNER, which can be used to facilitate various geographic applications with text.The materials include the following:data: Data from the preparation process.pre_model: Model storage files from the experimental process of the paper, which allow for direct testing without the need for retraining the model.LH-FGNER: Code for the method proposed in the paper (LH-FGNER), along with code for related experimental discussions, non-open-source baselines, etc. It also includes environment files for reproduction and a README file for guidance.