A hybrid deep learning framework for bacterial named entity recognition with domain features
Abstract Background Microbes have been shown to play a crucial role in various ecosystems. Many human diseases have been proved to be associated with bacteria, so it is essential to extract the interaction between bacteria for medical research and application. At the same time, many bacterial intera...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-019-3071-3 |
| _version_ | 1819176162820096000 |
|---|---|
| author | Xusheng Li Chengcheng Fu Ran Zhong Duo Zhong Tingting He Xingpeng Jiang |
| author_facet | Xusheng Li Chengcheng Fu Ran Zhong Duo Zhong Tingting He Xingpeng Jiang |
| author_sort | Xusheng Li |
| collection | DOAJ |
| description | Abstract Background Microbes have been shown to play a crucial role in various ecosystems. Many human diseases have been proved to be associated with bacteria, so it is essential to extract the interaction between bacteria for medical research and application. At the same time, many bacterial interactions with certain experimental evidences have been reported in biomedical literature. Integrating this knowledge into a database or knowledge graph could accelerate the progress of biomedical research. A crucial and necessary step in interaction extraction (IE) is named entity recognition (NER). However, due to the specificity of bacterial naming, there are still challenges in bacterial named entity recognition. Results In this paper, we propose a novel method for bacterial named entity recognition, which integrates domain features into a deep learning framework combining bidirectional long short-term memory network and convolutional neural network. When domain features are not added, F1-measure of the model achieves 89.14%. After part-of-speech (POS) features and dictionary features are added, F1-measure of the model achieves 89.7%. Hence, our model achieves an advanced performance in bacterial NER with the domain features. Conclusions We propose an efficient method for bacterial named entity recognition which combines domain features and deep learning models. Compared with the previous methods, the effect of our model has been improved. At the same time, the process of complex manual extraction and feature design are significantly reduced. |
| first_indexed | 2024-12-22T21:06:23Z |
| format | Article |
| id | doaj.art-44a5c14e85e94e3c8f2bf4f30845f4ba |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-22T21:06:23Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-44a5c14e85e94e3c8f2bf4f30845f4ba2022-12-21T18:12:40ZengBMCBMC Bioinformatics1471-21052019-12-0120S161910.1186/s12859-019-3071-3A hybrid deep learning framework for bacterial named entity recognition with domain featuresXusheng Li0Chengcheng Fu1Ran Zhong2Duo Zhong3Tingting He4Xingpeng Jiang5School of Computer, Central China Normal UniversitySchool of Computer, Central China Normal UniversityCollaborative & Innovation Center, Central China Normal UniversitySchool of Computer, Central China Normal UniversitySchool of Computer, Central China Normal UniversitySchool of Computer, Central China Normal UniversityAbstract Background Microbes have been shown to play a crucial role in various ecosystems. Many human diseases have been proved to be associated with bacteria, so it is essential to extract the interaction between bacteria for medical research and application. At the same time, many bacterial interactions with certain experimental evidences have been reported in biomedical literature. Integrating this knowledge into a database or knowledge graph could accelerate the progress of biomedical research. A crucial and necessary step in interaction extraction (IE) is named entity recognition (NER). However, due to the specificity of bacterial naming, there are still challenges in bacterial named entity recognition. Results In this paper, we propose a novel method for bacterial named entity recognition, which integrates domain features into a deep learning framework combining bidirectional long short-term memory network and convolutional neural network. When domain features are not added, F1-measure of the model achieves 89.14%. After part-of-speech (POS) features and dictionary features are added, F1-measure of the model achieves 89.7%. Hence, our model achieves an advanced performance in bacterial NER with the domain features. Conclusions We propose an efficient method for bacterial named entity recognition which combines domain features and deep learning models. Compared with the previous methods, the effect of our model has been improved. At the same time, the process of complex manual extraction and feature design are significantly reduced.https://doi.org/10.1186/s12859-019-3071-3Named entity recognitionBiomedical text miningConditional random fieldDeep learning |
| spellingShingle | Xusheng Li Chengcheng Fu Ran Zhong Duo Zhong Tingting He Xingpeng Jiang A hybrid deep learning framework for bacterial named entity recognition with domain features BMC Bioinformatics Named entity recognition Biomedical text mining Conditional random field Deep learning |
| title | A hybrid deep learning framework for bacterial named entity recognition with domain features |
| title_full | A hybrid deep learning framework for bacterial named entity recognition with domain features |
| title_fullStr | A hybrid deep learning framework for bacterial named entity recognition with domain features |
| title_full_unstemmed | A hybrid deep learning framework for bacterial named entity recognition with domain features |
| title_short | A hybrid deep learning framework for bacterial named entity recognition with domain features |
| title_sort | hybrid deep learning framework for bacterial named entity recognition with domain features |
| topic | Named entity recognition Biomedical text mining Conditional random field Deep learning |
| url | https://doi.org/10.1186/s12859-019-3071-3 |
| work_keys_str_mv | AT xushengli ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT chengchengfu ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT ranzhong ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT duozhong ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT tingtinghe ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT xingpengjiang ahybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT xushengli hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT chengchengfu hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT ranzhong hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT duozhong hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT tingtinghe hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures AT xingpengjiang hybriddeeplearningframeworkforbacterialnamedentityrecognitionwithdomainfeatures |