关键词: 命名实体识别, 自然语言处理, 知识图谱构建, 高效指针, 通用实体

Abstract: Aiming at the problem that most of the current named entity recognition models only use character-level information encoding and lack of text hierarchical information extraction, Chinese named entity recognition model incorporating Multi-granularity linguistic knowledge and Hierarchical informationa(CMH) was proposed. First, the text was encoded using a model that had been pre-trained with multi-granularity linguistic knowledge, so that the model could capture both fine-grained and coarse-grained linguistic information of the text, and thus better characterize the corpus. Second, hierarchical information extraction was performed using the ON-LSTM(Ordered Neurons Long Short Term Memory Network) model in order to utilize the hierarchical structural information of the text itself and enhance the temporal relationships between encodings. Finally, the text's disambiguation information was incorporated by the decoding end of the model, and the entity recognition problem was transformed into a table filling problem in order to better solve the entity overlapping problem and obtain more accurate entity recognition results.Meanwhile, in order to solve the problem of poor migration ability of the then-current model in different domains, the concept of universal entity recognition was proposed, and a set of universal named entity recognition dataset (MDNER) was constructed to enhance the generalization ability of the model in multiple domains by filtering the universal entity types in multiple domains To validate the effectiveness of the proposed model, experiments were conducted on the datasets Resume, Weibo, and MSRA, and the F1 values were improved by 0.94, 4.95, and 1.58 percentage points, respectively, to reach the optimal level when compared to the MECT (Multi-metadata Embedding based Cross-Transformer) model.Meanwhile, in order to verify the model's entity recognition effect in multi-domain, experiments were conducted on MDNER data, and the F1 value reached 95.29%. The experimental results show that the pre-training of multi-granularity linguistic knowledge, the extraction of structural information at the text hierarchy level, and the efficient pointer decoder are crucial for the performance of the model.

Key words: named entity recognition, natural language processing, knowledge graph construction, efficient pointer, generic entities