基于ERNIE-CRF-ESL安全隐患文本结构化解析

doi:10.13190/j.jbupt.2021-003

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (5): 107-113.doi: 10.13190/j.jbupt.2021-003

基于ERNIE-CRF-ESL安全隐患文本结构化解析

艾新波¹, 郭彦君², 谢云昊¹, 陈成¹

1. 北京邮电大学人工智能学院, 北京 100876;
2. 北京邮电大学现代邮政学院, 北京 100876

收稿日期:2021-02-03 出版日期:2021-10-28 发布日期:2021-09-06
作者简介:艾新波(1981-),男,副教授,博士生导师,E-mail:axb@bupt.edu.cn.
基金资助:
国家自然科学基金项目（61702047）

Structural Analysis of Hidden Danger Description Text Based on ERNIE-CRF-ESL

AI Xin-bo¹, GUO Yan-jun², XIE Yun-hao¹, CHEN Cheng¹

1. School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. School of Modern Post, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2021-02-03 Online:2021-10-28 Published:2021-09-06

摘要/Abstract

摘要： 安全隐患描述文本是通过自然语言描述进行记录的，具有主观随意性问题，现有的序列标注相关模型无法从中提取关键知识信息.根据安全隐患描述文本的特点，首先设计了一种适用于安全隐患描述文本的序列标注方法，提出了基于知识集成的增强表示（ERNIE）模型的进行词向量特征提取，在其基础上通过融合条件随机场（CRF）模块和信息提取（ESL）模块，构建了一种安全生产隐患描述文本结构化解析方法.在某超大城市的安全隐患描述文本上进行了实验，实验结果表明，所提模型在文本结构化解析任务的精确率达到了65.1%，可以从城市安全隐患非结构化数据中获取更多的知识信息，进而规范化安全隐患排查记录工作.

关键词: 安全隐患描述文本, 结构化解析, 序列标注模型

Abstract: The safety hazard description text is recorded by natural language description,which has the problem of subjective arbitrariness. The existing sequence annotation-related models cannot extract key knowledge information from the safety hazard description. Based on the characteristics of the safety hazard description text,a sequence annotation method is designed for the safety hazard description text,and the enhanced representation from knowledge integration (ERNIE) model is proposed for word vector feature extraction. Based on the conditional random fields (CRF) module and the information extraction (ESL) module,a structured parsing method of safety hazard description text is constructed. An experiment is carried out on a description text of a hidden safety hazard in a mega-city. The experimental results show that the proposed model achieves a 65.1% precision rate in the text structured parsing task. The proposed algorithm can obtain more knowledge information from the unstructured data of urban safety hazards,and then standardize the safety hazards investigation and recording work.

Key words: safety hazard description text, structural analysis, sequence labeling model

中图分类号:

TP181

艾新波, 郭彦君, 谢云昊, 陈成. 基于ERNIE-CRF-ESL安全隐患文本结构化解析[J]. 北京邮电大学学报, 2021, 44(5): 107-113.

AI Xin-bo, GUO Yan-jun, XIE Yun-hao, CHEN Cheng. Structural Analysis of Hidden Danger Description Text Based on ERNIE-CRF-ESL[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(5): 107-113.

参考文献

[1] Hirschmuller H. Stereo processing by semiglobal match-ing and mutual information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 30(2):328-341.
[2] Furukawa Y, Ponce J. Accurate, dense, and robust multiview stereopsis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 32(8):1362-1376.
[3] Vu H-H, Labatut P, Pons J-P, et al. High accuracy and visibility-consistent dense multiview stereo[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 34(5):889-901.
[4] Galliani S, Lasinger K, Schindler K. Massively parallel multiview stereopsis by surface normal diffusion[C]//IEEE International Conference on Computer Vision. Santiago:IEEE, 2015:873-881.
[5] Schönberger J L, Zheng Enliang, Frahm J M, et al. Pixel-wise view selection for unstructured multi-view stereo[C]//European Conference on Computer Vision. Amsterdam:Springer, 2016:501-518.
[6] Yao Yao, Luo Zixin, Li Shiwei, et al. MVSnet:depth inference for unstructured multi-view stereo[C]//European Conference on Computer Vision. Munich:Springer, 2018:767-783.
[7] Yao Yao, Luo Zixin, Li Shiwei, et al. Recurrent MVSnet for high-resolution multi-view stereo depth inference[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach:IEEE, 2019:5525-5534.
[8] Luo Keyang, Guan Tao, Ju Lili, et al. P-MVSnet:learning patch-wise matching confidence aggregation for multi-view stereo[C]//IEEE/CVF International Conference on Computer Vision. Long Beach:IEEE, 2019:10452-10461.
[9] Aanæs H, Jensen R R, Vogiatzis G, et al. Large-scale data for multiple-view stereopsis[J]. International Journal of Computer Vision, 2016, 120(2):153-168.
[10] Knapitsch A, Park J, Zhou Qianyi, et al. Tanks and temples:benchmarking large-scale scene reconstruction[J]. ACM Transactions on Graphics, 2017, 36(4):1-13.
[11] Angelova A, Long P M. Benchmarking large-scale fine-grained categorization[C]//IEEE Winter Conference on Applications of Computer Vision. Steamboat Springs:IEEE, 2014:532-539.
[12] Hartmann W, Galliani S, Havlena M, et al. Learned multi-patch similarity[C]//IEEE International Conference on Computer Vision. Venice:IEEE, 2017:1586-1594.
[13] Ji Mengqi, Gall J, Zheng Haitian, et al. Surfacenet:an end-to-end 3D neural network for multiview stereopsis[C]//IEEE International Conference on Computer Vision. Venice:IEEE, 2017:2307-2315.
[14] Choi S, Kim S, Park K, et al. Learning descriptor, confidence, and depth estimation in multi-view stereo[C]//IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City:IEEE, 2018:276-282.
[15] Zhu Guangming, Zhang Liang, Shen Peiyi, et al. Multimodal gesture recognition using 3-D convolution and convolutional LSTM[J]. IEEE Access, 2017, 5:4517-4524.
[16] Konolige K, Agrawal M. FrameSLAM:from bundle adjustment to real-time visual mapping[J]. IEEE Transactions on Robotics, 2008, 24(5):1066-1077.
[17] Tola E, Strecha C, Fua P. Efficient large-scale multi-view stereo for ultra high-resolution image sets[J]. Machine Vision and Applications, 2012, 23(5):903-920.

基于ERNIE-CRF-ESL安全隐患文本结构化解析

Structural Analysis of Hidden Danger Description Text Based on ERNIE-CRF-ESL

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	霍纬纲孟璐郭润夏. 融合重构和对比的多维时间序列表示学习模型[J]. 北京邮电大学学报, 2023, 46(4): 83-90.
[2]	孙艳华史亚会王朱伟李萌司鹏搏. 基于元蒸馏的个性化联邦学习算法[J]. 北京邮电大学学报, 2023, 46(1): 12-18.
[3]	王俊洁徐聪聪赵增瑞姜祎群徐军. 基于多分支压缩和激励网络的蕈样肉芽肿细胞分类[J]. 北京邮电大学学报, 2022, 45(4): 35-41.
[4]	王靖, 姜竹青, 门爱东, 郭晓强, 王智康. 阶梯式图像去噪方法[J]. 北京邮电大学学报, 2022, 45(1): 52-57.
[5]	韩越林, 王小玉. 多头自注意力在双曲空间下的点击率预测[J]. 北京邮电大学学报, 2021, 44(5): 127-132.
[6]	刘寒. 混合采样与遗传算法相结合的垃圾网页检测[J]. 北京邮电大学学报, 2019, 42(6): 111-117.
[7]	张晖, 刘姝, 赵海涛, 孙雁飞. 超密集场景下考虑业务动态的功率匹配算法[J]. 北京邮电大学学报, 2019, 42(5): 48-53.
[8]	仇利克, 刘竞, 孙中卫, 赵扬帆. 一种快速的特征选择框架和方法[J]. 北京邮电大学学报, 2019, 42(3): 127-132.
[9]	刘占峰, 潘甦. 基于模糊粗糙集实例选择的混合算法在信用评分中的应用[J]. 北京邮电大学学报, 2019, 42(2): 101-107.
[10]	张俐, 袁玉宇, 王枞. 基于最大相关信息系数的FCBF特征选择算法[J]. 北京邮电大学学报, 2018, 41(4): 86-90.
[11]	张晖, 王敏. 基于移动社交环境的用户行为最优关联预测[J]. 北京邮电大学学报, 2017, 40(6): 50-56.
[12]	仇利克, 郭忠文, 刘青, 刘颖健, 仇志金. 基于冗余分析的特征选择算法[J]. 北京邮电大学学报, 2017, 40(1): 36-41.
[13]	及歆荣, 侯翠琴, 侯义斌. 面向WSN的稀疏核学习机分布式训练方法[J]. 北京邮电大学学报, 2016, 39(3): 80-84.
[14]	董轶群, 徐文星, 刘建东, 王淑鸿, 江慧娜. 不确定边界区域间方向关系建模方法[J]. 北京邮电大学学报, 2016, 39(1): 18-23.
[15]	毕松, 韩存武, 孙德辉. 语用协同模型及其在背景建模中的应用[J]. 北京邮电大学学报, 2014, 37(5): 56-60.