Data and knowledge-driven named entity recognition for cyber security
Abstract Named Entity Recognition (NER) for cyber security aims to identify and classify cyber security terms from a large number of heterogeneous multisource cyber security texts. In the field of machine learning, deep neural networks automatically learn text features from a large number of dataset...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-05-01
|
| Series: | Cybersecurity |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42400-021-00072-y |
| _version_ | 1818646282815668224 |
|---|---|
| author | Chen Gao Xuan Zhang Hui Liu |
| author_facet | Chen Gao Xuan Zhang Hui Liu |
| author_sort | Chen Gao |
| collection | DOAJ |
| description | Abstract Named Entity Recognition (NER) for cyber security aims to identify and classify cyber security terms from a large number of heterogeneous multisource cyber security texts. In the field of machine learning, deep neural networks automatically learn text features from a large number of datasets, but this data-driven method usually lacks the ability to deal with rare entities. Gasmi et al. proposed a deep learning method for named entity recognition in the field of cyber security, and achieved good results, reaching an F1 value of 82.8%. But it is difficult to accurately identify rare entities and complex words in the text.To cope with this challenge, this paper proposes a new model that combines data-driven deep learning methods with knowledge-driven dictionary methods to build dictionary features to assist in rare entity recognition. In addition, based on the data-driven deep learning model, an attention mechanism is adopted to enrich the local features of the text, better models the context, and improves the recognition effect of complex entities. Experimental results show that our method is better than the baseline model. Our model is more effective in identifying cyber security entities. The Precision, Recall and F1 value reached 90.19%, 86.60% and 88.36% respectively. |
| first_indexed | 2024-12-17T00:44:10Z |
| format | Article |
| id | doaj.art-a712c172188a44d395728cbf0c5bd579 |
| institution | Directory Open Access Journal |
| issn | 2523-3246 |
| language | English |
| last_indexed | 2024-12-17T00:44:10Z |
| publishDate | 2021-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Cybersecurity |
| spelling | doaj.art-a712c172188a44d395728cbf0c5bd5792022-12-21T22:09:57ZengSpringerOpenCybersecurity2523-32462021-05-014111310.1186/s42400-021-00072-yData and knowledge-driven named entity recognition for cyber securityChen Gao0Xuan Zhang1Hui Liu2School of Software, Yunnan UniversitySchool of Software, Yunnan UniversitySchool of Software, Yunnan UniversityAbstract Named Entity Recognition (NER) for cyber security aims to identify and classify cyber security terms from a large number of heterogeneous multisource cyber security texts. In the field of machine learning, deep neural networks automatically learn text features from a large number of datasets, but this data-driven method usually lacks the ability to deal with rare entities. Gasmi et al. proposed a deep learning method for named entity recognition in the field of cyber security, and achieved good results, reaching an F1 value of 82.8%. But it is difficult to accurately identify rare entities and complex words in the text.To cope with this challenge, this paper proposes a new model that combines data-driven deep learning methods with knowledge-driven dictionary methods to build dictionary features to assist in rare entity recognition. In addition, based on the data-driven deep learning model, an attention mechanism is adopted to enrich the local features of the text, better models the context, and improves the recognition effect of complex entities. Experimental results show that our method is better than the baseline model. Our model is more effective in identifying cyber security entities. The Precision, Recall and F1 value reached 90.19%, 86.60% and 88.36% respectively.https://doi.org/10.1186/s42400-021-00072-yCyber securityNamed entity recognitionAttention mechanismDictionaryDeep learning |
| spellingShingle | Chen Gao Xuan Zhang Hui Liu Data and knowledge-driven named entity recognition for cyber security Cybersecurity Cyber security Named entity recognition Attention mechanism Dictionary Deep learning |
| title | Data and knowledge-driven named entity recognition for cyber security |
| title_full | Data and knowledge-driven named entity recognition for cyber security |
| title_fullStr | Data and knowledge-driven named entity recognition for cyber security |
| title_full_unstemmed | Data and knowledge-driven named entity recognition for cyber security |
| title_short | Data and knowledge-driven named entity recognition for cyber security |
| title_sort | data and knowledge driven named entity recognition for cyber security |
| topic | Cyber security Named entity recognition Attention mechanism Dictionary Deep learning |
| url | https://doi.org/10.1186/s42400-021-00072-y |
| work_keys_str_mv | AT chengao dataandknowledgedrivennamedentityrecognitionforcybersecurity AT xuanzhang dataandknowledgedrivennamedentityrecognitionforcybersecurity AT huiliu dataandknowledgedrivennamedentityrecognitionforcybersecurity |