高质量文本数据驱动的命名实体识别加速镍基单晶高温合金材料知识发现

刘悦, 姚文轩, 刘大晖, 丁琳, 杨正伟, 刘微, 于涛, 施思齐

Named Entity Recognition Driven by High-Quality Text Data Accelerates the Knowledge Discovery of Nickel-Based Single Crystal Superalloys

LIU Yue, YAO Wenxuan, LIU Dahui, DING Lin, YANG Zhengwei, LIU Wei, YU Tao, SHI Siqi

表1 不同模型在数据集A_DomainDictionary上的准确率、召回率和F1值

Table 1 Precision, recall, and F1-score of different models on dataset A_DomainDictionary

Model Precision Recall F1-score BERT-Bi-GRU-CRF 0.57 0.62 0.60 Bi-LSTM(Glove)-CRF 0.80 0.81 0.80 Bi-LSTM(OneHot)-CRF 0.81 0.81 0.81 Bi-LSTM(OneHot-Glove)-CRF 0.82 0.83 0.82 SF-NER 0.84 0.84 0.84