| 基于BiLSTM-IDCNN-CRF模型的生态治理技术领域命名实体识别 |
| |
| 引用本文： | 蒋翔,马建霞,袁慧. 基于BiLSTM-IDCNN-CRF模型的生态治理技术领域命名实体识别[J]. 计算机应用与软件, 2021, 38(3): 134-141. DOI: 10.3969/j.issn.1000-386x.2021.03.020 |
| |
| 作者姓名： | 蒋翔 马建霞 袁慧 |
| |
| 作者单位： | 中国科学院西北生态环境资源研究院 甘肃 兰州 730000;中国科学院兰州文献情报中心 甘肃 兰州 730000;中国科学院大学经济与管理学院图书情报与档案管理系 北京 100190;中国科学院西北生态环境资源研究院 甘肃 兰州 730000;中国科学院兰州文献情报中心 甘肃 兰州 730000;中国移动通信集团北京有限公司 北京 100007 |
| |
| 基金项目： | 国家自然科学基金项目;国家重点研发计划项目 |
| |
| 摘 要： | 在生态治理技术领域中,有大量的文献数据没有得到充分的开发与利用.提出基于字嵌入的BiL-STM-IDCNN-CRF模型,结合BiLSTM网络和IDCNN网络获取到的不同粒度的特征.在生态治理技术数据集中取得的F1值为0.7207,均高于现有主流模型取得的成绩.实验验证了字嵌入方法的有效性和模型的性能,同时也为其他文本书...
|
| 关 键 词： | 命名实体识别 自然语言处理 生态治理技术 神经网络 字嵌入 |
NAMED ENTITY RECOGNITION IN THE FIELD OF ECOLOGICAL MANAGEMENT TECHNOLOGY BASED ON BILSTM-IDCNN-CRF MODEL |
| |
| Jiang Xiang,Ma Jianxia,Yuan Hui. NAMED ENTITY RECOGNITION IN THE FIELD OF ECOLOGICAL MANAGEMENT TECHNOLOGY BASED ON BILSTM-IDCNN-CRF MODEL[J]. Computer Applications and Software, 2021, 38(3): 134-141. DOI: 10.3969/j.issn.1000-386x.2021.03.020 |
| |
| Authors: | Jiang Xiang Ma Jianxia Yuan Hui |
| |
| Affiliation: | (Northwest Institute of Eco-Environment and Resource,Chinese Academy of Sciences,Lanzhou 730000,Gansu,China;Lanzhou Information Center,Chinese Academy of Sciences,Lanzhou 730000,Gansu,China;Department of Library Information and Archives Management,School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China;China Mobile Communications Group Beijing Co.,Ltd.,Beijing 100007,China) |
| |
| Abstract: | In the field of ecological management technology,a large amount of literature data has not been fully developed and utilized.A BiLSTM-IDCNN-CRF model based on character embedding is proposed,which combines the different granularity characteristics obtained by BiLSTM network and IDCNN network.The F1 value obtained in the ecological management technology data set was 0.7207,which was higher than the existing mainstream models.The experiments verify the effectiveness of the character embedding method and the performance of the BiLSTM-IDCNN-CRF model,and it provids ideas for the named entity recognition in other fields with different text writing norms and strong professionalism. |
| |
| Keywords: | Named entity recognition Natural language processing Ecological management technology Neural network Character embedding |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
