We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
A hybrid deep learning framework for bacterial named entity recognition with domain features.
- Authors
Xusheng Li; Chengcheng Fu; Ran Zhong; Duo Zhong; Tingting He; Xingpeng Jiang
- 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.
- Subjects
ARTIFICIAL neural networks; BLENDED learning; DEEP learning; NAMED-entity recognition; SHORT-term memory; FEATURE extraction
- Publication
BMC Bioinformatics, 2019, Vol 20, p1
- ISSN
1471-2105
- Publication type
Article
- DOI
10.1186/s12859-019-3071-3