ner dataset and code of paper "Accelerating the Exploration of Information in Chinese Geological Texts Using Pretrained Model and Self Attention"

The datasets and code used in this study are publicly available.Datasets:The datasets used in this study have been divided into training, testing, and validation sets.Code:This code repository includes Python scripts that replicate the experimental setup described in the paper. The code is organized into the following modules:Data Preprocessing: This module contains code for loading, cleaning, and transforming the datasets.Model Training: This module includes code for training various named entity recognition models using pre-trained language models. The code also includes implementations of the ablation experiments and data augmentation techniques described in the paper.Evaluation: This module contains code for evaluating the performance of the trained models on the held-out data sets.The data and code are provided to facilitate reproducibility and further research on named entity recognition in the Chinese language.<br><b>Clarification: None of the authors are affiliated with Tsinghua University.</b>