基于Bi-LSTM-CRF算法的气象预警信息质控系统的实现

doi:10.3969/j.issn.1006-2475.2019.06.019

计算机与现代化

基于Bi-LSTM-CRF算法的气象预警信息质控系统的实现

(1.安徽省公共气象服务中心,安徽合肥230031;2.安徽大学电气工程与自动化学院,安徽合肥230039)

收稿日期:2019-01-29 出版日期:2019-06-14 发布日期:2019-06-14
作者简介:张淑静(1981-),女,安徽阜阳人,工程师,学士,研究方向:计算机应用,E-mail: 78673452@qq.com; 通信作者:苗开超(1973-),男,高级工程师,硕士,研究方向:计算机应用,专业气象服务; 张亚力(1990-),女,助理工程师,硕士,研究方向:计算机应用; 杨彬(1964-),男,高级工程师,学士,研究方向:大气科学; 李腾(1981-),男,教授,博士,研究方向:人工智能; 刘宜轩(1983-),女,工程师,硕士,研究方向:计算机应用; 汪翔(1985-),男,高级工程师,硕士,研究方向:气象学。
基金资助:
国家自然科学基金资助项目(41575155)

Implementation of Quality Control Systems Based on Bi-LSTM-CRF #br# Algorithm for Meteorological Warning Information

(1. Anhui Public Meteorological Service Center, Hefei 230031, China;
2. School of Electrical Engineering and Automation, Anhui University, Hefei 230039, China)

Received:2019-01-29 Online:2019-06-14 Published:2019-06-14

摘要/Abstract

摘要： 本文采用双向长短期记忆网络条件随机场（Bi-LSTM-CRF）算法，通过双向循环神经网络（Bi-LSTM）对已有的合法预警信息文本数据集和开放域中文分析公开数据集进行训练；采用CRF序列标注法有效地结合了预警前后的标签信息对分词进行序列标注；使用该算法建立的气象预警信息质控系统已应用在安徽省突发事件预警信息发布系统，在实际应用的过程中充分证明基于神经网络的气象预警信息质控系统能直接有效地对新的预警信息中可能含有的敏感字（词）、错别字等进行智能监测，以帮助监测人员进行气象预警判断，从而可以对发布的气象预警信息起到质量把关的作用。

关键词: Bi-LSTM-CRF, 中文分词, 气象预警, 信息质控, 智能检测

Abstract: This paper adopts the bi-directional long short-term memory conditional random field (Bi-LSTM-CRF) algorithm to train the existing legal early-warning information database and the open domain Chinese parsing database through the bi-directional long short-term memory. At the same time, the conditional random field (CRF) model is used to label the word segmentation by effectively combining the label information before and after the warning. The quality control system of meteorological early-warning information based on the above algorithm has already been applied in the emergency warning information issuing system of Anhui Province. In the process of practical application, it has been proved that such system can directly and effectively monitor sensitive keywords and misspellings in the upcoming warning information, so as to help monitoring stuff make better judgments and play an important role in the quality controls of the issued weather warning information.

Key words: Bi-LSTM-CRF, Chinese word segmentation, meteorological warning, information quality control, intelligent monitoring

中图分类号:

TP391

张淑静1,苗开超1,张亚力1,杨彬1,李腾2,刘宜轩1,汪翔1. 基于Bi-LSTM-CRF算法的气象预警信息质控系统的实现[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2019.06.019.

ZHANG Shu-jing1, MIAO Kai-chao1, ZHANG Ya-li1, YANG Bin1, LI Teng2, LIU Yi-xuan1, WANG Xiang1. Implementation of Quality Control Systems Based on Bi-LSTM-CRF #br# Algorithm for Meteorological Warning Information[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.06.019.

参考文献

［1］曹之玉,赵晶晶. 预警质量控制技术研究［J］. 科技成果管理与研究, 2017,131(9):40-43.
［2］孙健,姚秀萍,王丽娟,等. 我国气象预警信息覆盖率的初步分析［J］. 气象科技进展, 2013,3(5):19-23.
［3］百家号. 暴雨天，小心“短时强僵尸”出没［N］．环球时报公号, 2018-08-12.
［4］ KWOK K L. A neural network for probabilistic information retrieval［J］. ACM SIGIR Forum, 1989,23(SI):21-30.
［5］〖JP4〗BAHDANAU D, CHO K, BENGIO Y. Neural Machine Translation by Jointly Learning to Align and Translate［DB/OL］. (2015-05-19)［2019-01-29］. https://arxiv.org/pdf/1409.0473.pdf.
［6］ SANTOS C N D, GATTIT M. Deep convolutional neural networks for sentiment analysis of short texts［C］// Proceedings of the 25th International Conference on Computational Linguistics. 2014:69-78.
［7］ SAGARA T, HAGIWARA M. Natural language neural network and its application to question-answering system［J］. Neurocomputing, 2014,142(1):201-208.
［8］ LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural Architectures for Named Entity Recognition［DB/OL］. (2016-04-07)［2019-01-29］. https://arxiv.org/pdf/1603.01360.pdf.
［9］ CHEN X C, QIU X P, ZHU C X, et al. Long short-term memory neural networks for Chinese word segmentation［C］// Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing. 2015:1197-1206.
［10］YAO Y S, HUANG Z. Bi-directional LSTM recurrent neural network for Chinese word segmentation［C］// Proceedings of 2016 International Conference on Neural Information Processing. 2016:345-353.
［11］MA X Z, HOVY E. End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF［DB/OL］. (2015-05-29)［2019-01-29］. https://arxiv.org/pdf/1603.01354.pdf.
［12］胡锡衡. 正向最大匹配法在中文分词技术中的应用［J］. 鞍山师范学院学报, 2008,10(2):42-45.
［13］ZHEN L, LI Y S. Reverse backtracking research of Chinese segmentation based on dictionary of hash structure［C］// Proceedings of 2010 2nd International Conference on Information Technology & Computer Science. 2010:265-267.
［14］王靖. 基于机械切分和标注的中文分词研究［D］. 长沙:湖南大学, 2009.
［15］RABINER L R, JUANG B H. An introduction to hidden Markov models［J］. IEEE ASSP Magazine, 1986,3(1):4-16.
［16］BERGER A L, PIETRA V J D, PIETRA S A D. A maximum entropy approach to natural language processing［J］. Computational Linguistics, 1996,22(1):39-71.
［17］LAFFERTY J, MCCALLUM A, PEREIRA F C N. Conditional random fields: Probabilistic models for segmenting and labeling sequence data［J］. Proceedings of ICML, 2001,3(2):282-289.
［18］DENG L, YU D. Deep learning: Methods and applications［J］. Foundations & Trends in Signal Processing, 2014,7(3):197-387.
［19］GRAVES A. Long Short-term Memory［M］// Supervised Sequence Labeling with Recurrent Neural Networks. Springer, 2012:37-45.
［20］HOCHREITER S, SCHMIDHUBER J. Long short-term memory［J］. Neural Computation, 1997,9(8):1735-1780.
［21］SINGH B, MARKS T K, JONES M, et al. A multi-stream bi-directional recurrent neural network for fine-grained action detection［C］// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:1961-1970.
［22］LIN B Y, XU F, LUO Z, et al. Multi-channel Bi-LSTM-CRF model for emerging named entity recognition in social media［C］// Proceedings of the 3rd Workshop on Noisy User-generated Text. 2017:160-165.

[1]	周慧, 徐名海, 许晓东. 基于Attention-BIGRU-CRF的中文分词模型[J]. 计算机与现代化, 2022, 0(08): 7-12.
[2]	冯光;乔丹丹;常静怡. 基于分词匹配的主观题自动评阅技术研究[J]. 计算机与现代化, 2013, 1(3): 212-214,.
[3]	穆俊鹏;董魁锋;张明. 基于动态特征库的电子邮件分类的研究[J]. 计算机与现代化, 2012, 203(7): 120-123.
[4]	穆俊鹏;董魁锋;张明. 基于动态特征库的电子邮件分类的研究[J]. 计算机与现代化, 2012, 203(7): 120-123.
[5]	孟莎莎;王涛涛. 基于PLC的远程智能检测控制系统的设计[J]. 计算机与现代化, 2012, 208(12): 69-72.
[6]	杨伟超;刘阳;李淑霞. 基于搜索引擎的一站式检索平台设计与实现[J]. 计算机与现代化, 2012, 1(11): 220-222.
[7]	姜文志;顾佼佼;胡文萱;栗飞. 条件随机场模型的应用研究及改进[J]. 计算机与现代化, 2011, 1(11): 55-4.
[8]	孙殿哲;魏海平;陈岩. Nutch中庖丁解牛中文分词的实现与评测[J]. 计算机与现代化, 2010, 1(6): 187-0190.

基于Bi-LSTM-CRF算法的气象预警信息质控系统的实现

Implementation of Quality Control Systems Based on Bi-LSTM-CRF #br# Algorithm for Meteorological Warning Information

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价