Named Entity Recognition (NER) is a fundamental task in natural language processing that aims to identify and categorize named entities within unstructured text. In recent years, with the development of deep learning techniques, pre-trained language models have been widely used in NER tasks. However, these models still face limitations in terms of their scalability and adaptability, especially when dealing with complex linguistic phenomena such as nested entities and long-range dependencies. To address these challenges, we propose the MacBERT-BiGRU-Self Attention-Global Pointer (MB-GAP) model, which integrates MacBERT for deep semantic understanding, BiGRU for rich contextual information, self-attention for focusing on relevant parts of the input, and a global pointer mechanism for precise entity boundary detection. By optimizing the number of attention heads and global pointer heads, our model achieves an effective balance between complexity and performance. Extensive experiments on benchmark datasets, including ResumeNER, CLUENER2020, and SCHOLAT-School, demonstrate significant improvements over baseline models.
Community detection in social networks is one of the most important topics of network science. Researchers have developed numerous methods from various perspectives. However, the existing methods often overlook the team information encoded as a special type of user relation in the social network, which plays an important role in community formation and evolution. In this paper, we propose a novel community detection algorithm called Team-aware Community Detection (TaCD). Our model constructs a multi-view network by encoding the user interaction information as the user view and the team information as the team view. To measure the consistency across the two views, we use the Jaccard similarity to establish a cross-view coupling. Based on the constructed 2-view network, we use multi-view modularity to discover team-aware community structure, and solve the optimization problem using the well-known Generalized Louvain approach. Another contribution of this paper is the collection of a new SCHOLAT dataset, which consists of several social networks with team information and is publicly available for testing purposes. Our experimental results on several SCHOLAT networks with team information demonstrate that TaCD outperforms the existing community detection algorithms.