1.School of Computer Science & Engineering,Northeastern University,Shenyang 110169,China
2.China Software Information System Engineering Co. Ltd. ,Beijing 100081,China. Corresponding author: LIU Jun,E-mail: liujun@cse. neu. edu. cn
Show less
文章历史+
Received
Accepted
Published
2024-12-24
Issue Date
2026-03-26
PDF (1780K)
摘要
随着航空运输业与信息技术的快速发展,航空应急管理给海量、异构的航空安全数据高效利用带来了挑战.本文针对航空事故知识图谱的知识抽取问题,即命名实体识别与关系抽取问题,提出以下方法:1) 提出基于BERT(bidirectional encoder representations from Transformers)的改进BiGRU-IDCNN-CRF模型,实现94.69%的命名实体识别精确率;2) 构建基于强化学习的聚类远程监督关系抽取模型,结合改进K均值聚类与远程监督标注降低数据噪声,并通过强化学习优化去噪过程,最终结合分段卷积神经网络(PCNN)与注意力机制,实现84.16%的关系抽取精确率.实验结果表明,本文方法有效提升了航空事故知识图谱的信息提取质量,为航空安全管理提供了精准的信息支撑.
Abstract
In light of the rapid development of air transportation and information technology, the efficient utilization of massive and heterogeneous aviation safety data in aviation emergency management faces challenges. The problem of knowledge extraction for an aviation accident knowledge graph was studied, specifically named entity recognition and relation extraction, and the following methods were proposed: 1) An improved BiGRU-IDCNN-CRF model based on bidirectional encoder representations from Transformers (BERT) was presented, achieving a named entity recognition accuracy of 94.69%; 2) A reinforcement learning-based clustering distant supervision relation extraction model was constructed, in which data noise was reduced by integrating improved K-means clustering with distant supervision labeling, and the denoising process was optimized via reinforcement learning; a combination of piecewise convolutional neural network (PCNN) and an attention mechanism was applied to achieve a relation extraction accuracy of 84.16%. Experimental results indicate that the quality of information extraction for the aviation accident knowledge graph is effectively improved, providing accurate information support for aviation safety management.
经过注意力机制得到的向量输入到卷积层中,则句子长度为l,卷积核为g,填充长度为g-l,卷积层输出特征向量为 c .在池化层中,由卷积层的特征向量 C 与关系类型向量 R 计算相似度,得到注意力权重向量 e,通过将 e 和 W 进行乘法运算得到向量 Y,进行池化操作得到长度为3的向量.最终将分段池化输出拼接并经过tanh激活函数得到最终输出 z .具体计算公式如下:
其中:k是使用卷积核的数量;n是定义的关系向量总数,本文中n=7;pi∶n 为分段后的所有池化输出pi 进行拼接后的池化层总输出; F 为参数向量; Wi 为句子特征向量.
DatasetQ数据集构建基于中国民用航空安全信息系统网站和航空安全自愿报告系统网站上的公开信息.首先,通过对原始文本进行清洗与标注,形成基础语料.随后,该基础语料经历了两阶段的数据增强流程:第一阶段采用EDA(exploratory data analysis)方法以增加数据的多样性;第二阶段在此基础上,进一步应用TF-IDF方法进行深度语义层面的扩充与生成,最终形成了总规模达43 224条数据的数据集,该数据集按4∶1的比例划分为训练集与测试集,用于后续的模型训练与性能验证.
ZhangRu-jia, DaiLu, WangBang, et al. Recent advances of Chinese named entity recognition based on deep learning[J]. Journal of Chinese Information Processing, 2022, 36(6): 20-35.
[4]
GollerC, KuchlerA. Learning task-dependent distributed representations by backpropagation through structure[C]//Proceedings of International Conference on Neural Networks (ICNN’96). Washington DC, 1996: 347-352.
[5]
GersF A, SchmidhuberJ, CumminsF. Learning to forget: continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
[6]
QinQ L, ZhaoS, LiuC M. A BERT-BiGRU-CRF model for entity recognition of Chinese electronic medical records[J]. Complexity, 2021, 2021: 6631837.
[7]
LiZ R, HuC M, GuoX H, et al. An unsupervised multiple-task and multiple-teacher model for cross-lingual named entity recognition[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin, 2022: 170-179.
[8]
BoudjellalN, ZhangH P, KhanA, et al. ABioNER: a BERT-based model for Arabic biomedical named-entity recognition[J]. Complexity, 2021, 2021: 6633213.
[9]
ZhouR, LiX, BingL D, et al. Improving self-training for cross-lingual named entity recognition with contrastive and prototype learning[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Toronto, 2023: 4018-4031.
[10]
MaJ, BallesterosM, DossS, et al. Label semantics for few shot named entity recognition[C]//Findings of the Association for Computational Linguistics: ACL 2022. Dublin,2022: 1956-1971.
Hai-hongE, ZhangWen-jing, XiaoSi-qi, et al. Survey of entity relationship extraction based on deep learning [J]. Journal of Software,2019,30(6):1793-1818.
[13]
HeH, GanjamK, JainN, et al. An insight extraction system on BioMedical literature with deep neural networks[C]//Proceedings of the 2017 Conference on Empirical Methods in NaturalLanguage Processing. Copenhagen, 2017: 2691-2701.
[14]
ZhangM S, ZhangY, FuG H. End-to-end neural relation extraction with global optimization[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, 2017: 1730-1740.
[15]
YangS Z, LiuY X, ZhangK W, et al. Overview of remote supervision relationship extraction[J].Journal of Computer Science, 2021, 44(8):1636-1660.
XuXin-ran, WangTeng-yu, LuCai. Research progress of graph neural network in knowledge graph construction and application[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2278-2299.
ZhengZhi-yun, XuYa-mei, LiLun, et al. Distantly supervised relation extraction with position feature attention and relation enhancement[J].Journal of Chinese Computer Systems, 2023, 44(12):2678-2684.
[20]
WangG Y, ZhangW, WangR X, et al. Label-free distant supervision for relation extraction via knowledge graph embedding[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, 2018: 2246-2255.
[21]
JiG L, LiuK, HeS Z, et al. Distant supervision for relation extraction with sentence-level attention and entity descriptions[C]// Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco, 2017: 3060-3066.
[22]
ChenT, ShiH Z, TangS L, et al. CIL: contrastive instance learning framework for distantly supervised relation extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics. Online, 2021: 6191-6200.
[23]
LuoB F, FengY S, WangZ, et al. Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver,2017: 430-439.
[24]
ZhouY R, PanL M, BaiC Y, et al. Self-selective attention using correlation between instances for distant supervision relation extraction[J]. Neural Networks, 2021, 142: 213-220.
[25]
MintzM, BillsS, SnowR, et al. Distant supervision for relation extraction without labeled data[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Singapore, 2009: 1003-1011.
[26]
HoffmannR, ZhangC L, LingX, et al. Knowledge-based weak supervision for information extraction of overlapping relations[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Portland, 2011: 541-550.
[27]
SurdeanuM, TibshiraniJ, NallapatiR, et al. Multi-instance multi-label learning for relation extraction[C]//Conference on Empirical Methods in Natural Language Processing. Jeju Island, 2012:455-465.