CLC number: TP393.08
On-line Access: 2019-07-08
Received: 2018-08-31
Revision Accepted: 2019-03-11
Crosschecked: 2019-06-11
Cited: 0
Clicked: 6898
Ya Qin, Guo-wei Shen, Wen-bo Zhao, Yan-ping Chen, Miao Yu, Xin Jin. A network security entity recognition method based on feature template and CNN-BiLSTM-CRF[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(6): 872-884.
@article{title="A network security entity recognition method based on feature template and CNN-BiLSTM-CRF",
author="Ya Qin, Guo-wei Shen, Wen-bo Zhao, Yan-ping Chen, Miao Yu, Xin Jin",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="20",
number="6",
pages="872-884",
year="2019",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1800520"
}
%0 Journal Article
%T A network security entity recognition method based on feature template and CNN-BiLSTM-CRF
%A Ya Qin
%A Guo-wei Shen
%A Wen-bo Zhao
%A Yan-ping Chen
%A Miao Yu
%A Xin Jin
%J Frontiers of Information Technology & Electronic Engineering
%V 20
%N 6
%P 872-884
%@ 2095-9184
%D 2019
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1800520
TY - JOUR
T1 - A network security entity recognition method based on feature template and CNN-BiLSTM-CRF
A1 - Ya Qin
A1 - Guo-wei Shen
A1 - Wen-bo Zhao
A1 - Yan-ping Chen
A1 - Miao Yu
A1 - Xin Jin
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 20
IS - 6
SP - 872
EP - 884
%@ 2095-9184
Y1 - 2019
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1800520
Abstract: By network security threat intelligence analysis based on a security knowledge graph (SKG), multi-source threat intelligence data can be analyzed in a fine-grained manner. This has received extensive attention. It is difficult for traditional named entity recognition methods to identify mixed security entities in Chinese and English in the field of network security, and there are difficulties in accurately identifying network security entities because of insufficient features extracted. In this paper, we propose a novel FT-CNN-BiLSTM-CRF security entity recognition method based on a neural network CNN-BiLSTM-CRF model combined with a feature template (FT). The feature template is used to extract local context features, and a neural network model is used to automatically extract character features and text global features. Experimental results showed that our method can achieve an F-score of 86% on a large-scale network security dataset and outperforms other methods.
[1]Bergstra J, Bengio Y, 2012. Random search for hyperparameter optimization. J Mach Learn Res, 13(1):281-305.
[2]Chiu JPC, Nichols E, 2015. Named entity recognition with bidirectional LSTM-CNNs. https://arxiv.org/abs/1511.08308
[3]Collobert R, Weston J, 2008. A unified architecture for natural language processing: deep neural networks with multitask learning. Proc ACM 25th Int Conf on Machine Learning, p.160-167.
[4]Collobert R, Weston J, Bottou L, et al., 2011. Natural language processing (almost) from scratch. J Mach Learn Res, 12(1):2493-2537.
[5]Dong CH, Zhang JJ, Zong CQ, et al., 2016. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. In: Lin CY, Xue N, Zhao D, et al. (Eds.), Natural Language Understanding and Intelligent Applications. Springer, Cham, p.239-250.
[6]Dos Santos C, Guimarães V, 2015. Boosting named entity recognition with neural character embeddings. Proc 5th Named Entity Workshop, joint with 53rd ACL and the 7th IJCNLP, p.25-33.
[7]Feng YH, Yu H, Sun G, et al., 2018. Named entity recognition method based on BLSTM. Comput Sci, 45(2):261-268 (in Chinese).
[8]Finkel JR, Manning CD, 2009. Joint parsing and named entity recognition. Human Language Technologies: the Annual Conf of the North American Chapter of the Association of Computational Linguistics, p.326-334.
[9]Gers FA, Schmidhuber A, Cummins F, 2000. Learning to forget: continual prediction with LSTM. Neur Comput, 12(10):2451-2471.
[10]Goller C, Kuchler A, 1996. Learning task-dependent distributed representations by backpropagation through structure. Proc Int Conf on Neural Networks, p.347-352.
[11]Hammerton J, 2003. Named entity recognition with long short-term memory. Proc 7th Conf on Natural Language Learning at HLT-NAACL, p.172-175.
[12]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.
[13]Huang ZH, Wei X, Kai Y, 2015. Bidirectional LSTM-CRF models for sequence tagging. https://arxiv.org/abs/1508.01991
[14]Joshi A, Lal R, Finin T, et al., 2013. Extracting cybersecurity related linked data from text. IEEE 7th Int Conf on Semantic Computing, p.252-259.
[15]Koeling R, 2000. Chunking with maximum entropy models. Proc 2nd Workshop on Learning Language in Logic and the 4th Conf on Computational Natural Language Learning, p.139-141.
[16]Lafferty JD, McCallum A, Pereira FCN, 2001. Conditional random fields: probabilistic models for segmenting and labeling sequence data. 18th Int Conf on Machine Learning, p.282-289.
[17]Lample G, Ballesteros M, Subramanian S, et al., 2016. Neural architectures for named entity recognition. Proc NAACL- HLT, p.260-270.
[18]LéCun Y, Bottou L, Bengio Y, et al., 1998. Gradient-based learning applied to document recognition. Proc IEEE, 86(11):2278-2324.
[19]Li JH, 2016. Overview of the technologies of threat intelligence sensing, sharing and analysis in cyber space. Chin J Network Inform Secur, 2(2):16-29 (in Chinese).
[20]Liu W, Li Y, Duan H, et al., 2016. Knowledge graph construction techniques. J Comput Res Dev, 53(3):582-600 (in Chinese).
[21]Luo G, Huang XJ, Li CY, et al., 2015. Joint named entity recognition and disambiguation. Proc Conf on Empirical Methods in Natural Language Processing, p.879-888.
[22]Ma XZ, Hovy E, 2016. End-to-end sequence labeling via bi- directional LSTM-CNNs-CRF.
[23]Mikolov T, Chen K, Corrado G, et al., 2013a. Efficient estimation of word representations in vector space. https://arxiv.org/abs/1301.3781
[24]Mikolov T, Sutskever I, Chen K, et al., 2013b. Distributed representations of words and phrases and their compositionality. https://arxiv.org/abs/1310.4546
[25]Passos A, Kumar V, McCallum A, 2014. Lexicon infused phrase embeddings for named entity resolution. Proc 18th Conf on Computational Language Learning, p.78-86.
[26]Peng NY, Dredze M, 2015. Named entity recognition for Chinese social media with jointly trained embeddings. Proc Conf on Empirical Methods in Natural Language Processing, p.548-554.
[27]Pennington J, Socher R, Manning C, 2014. Glove: global vectors for word representation. Proc Conf on Empirical Methods in Natural Language Processing, p.1532-1543.
[28]Pham V, Bluche T, Kermorvant C, et al., 2014. Dropout improves recurrent neural networks for handwriting recognition. 14th Int Conf on Frontiers in Handwriting Recognition, p.285-290.
[29]Qiu QQ, Miao DQ, Zhang ZF, 2013. Named entity recognition on Chinese microblog. Comput Sci, 40(6):196-198 (in Chinese).
[30]Rabiner LR, 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE, 77(2):257-286.
[31]Tang BZ, Cao HX, Wang XL, et al., 2014. Evaluating word representation features in biomedical named entity recognition tasks. Biomed Res Int, 2014:240403.
[32]Yang YM, 1999. An evaluation of statistical approaches to text categorization. Inform Retriev, 1(1-2):69-90.
[33]Yu HK, Zhang HP, Liu Q, et al., 2006. Chinese named entity identification using cascaded hidden Markov model. J Commun, 27(2):87-94 (in Chinese).
[34]Zhang XY, Wang T, Chen HW, 2005. Research on named entity recognition. Comput Sci, 32(4):44-48 (in Chinese).
Open peer comments: Debate/Discuss/Question/Opinion
<1>