当前位置: 首页 > 文章 > 面向农作物病虫害领域的命名实体识别 内蒙古农业大学学报(自然科学版) 2022 (1) 86-90
Position: Home > Articles > Named Entity Recognition for Crop Diseases and Insect Pests Journal of Inner Mongolia Agricultural University(Natural Science Edition) 2022 (1) 86-90

面向农作物病虫害领域的命名实体识别

作  者:
谢聪娇;高静;陈俊杰
单  位:
内蒙古农业大学计算机与信息工程学院;内蒙古自治区大数据中心;内蒙古自治区农牧业大数据研究与应用重点实验室
关键词:
命名实体识别;Bi-LSTM;CRF;病虫害
摘  要:
命名实体识别是信息抽取的基础任务,面向农作物病虫害领域的命名实体识别对于农业信息化建设具有重要意义。为了提高面向农作物病虫害领域命名实体识别的准确率,提出了采用字符级词性标注与自定义领域词典结合双向长短时记忆网络(Bi-LSTM)+条件随机场模型(CRF)的方法对"病虫害"、"作物"、"地名"、"农药"4类实体词进行识别,该方法的准确率达到了97.10%,因此该模型能够有效应用于农作物病虫害领域的命名实体识别任务。
译  名:
Named Entity Recognition for Crop Diseases and Insect Pests
作  者:
XIE Congjiao;GAO Jing;CHEN Junjie;College of Computer and Information Engineering,Inner Mongolia Agricultural University;Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture;Big Data Center of Inner Mongolia Autonomous Region;
关键词:
Named entity recognition;;Bi-LSTM;;CRF;;Pests and diseases
摘  要:
The named entity recognition is the basic part of the information extraction,and the named entity recognition for crop diseases and insect pests is significant for the agricultural information construction. In order to improve the accuracy of the named entity recognition in the field of crop diseases and insect pests,the method of character level part of speech tagging and user-defined domain dictionary combined with Bi-LSTM and CRF was proposed to identify four kinds of entity words of "pest", "crop", "place",and "pesticide". The experiments demenstrated that the accuracy of the method was 97. 10%,indicating that the model could be effectively applied to the named entity recognition task in the field of crop diseases and insect pests.

相似文章

计量
文章访问数: 13
HTML全文浏览量: 0
PDF下载量: 1

所属期刊

推荐期刊