Abstract | ||
---|---|---|
Learning and identifying key concepts from past fault records are essential for us to understand the causes of these faults, which lay the foundation for the fault diagnosis and prognosis. At present, faults in many fields (e.g., rail, automobile, and smart grid) are recorded in textual form. Due to the lack of effective mining and analysis tools, latent information in the massive textual data (text records) has not been fully unearthed. In this paper, a novel Adversarial Training-based Lattice LSTM model called AT-Lattice is proposed to address this problem. In this model, the Named Entity Recognition (NER) is achieved by Lattice LSTM and Conditional Random Field (CRF), where the Lattice LSTM is used to provide sequence information between words, and the CRF is used to get the final entity prediction result. In addition, the Chinese Word Segmentation (CWS) task is introduced to conduct the adversarial training with the NER task. The framework of the adversarial training is able to make full use of the boundary information and filter out the noise caused by the introduced CWS task. More importantly, extensive experiments are conducted on five different train fault datasets collected by a rail transit company. The results demonstrate that the proposed model outperforms the state-of-the-art baselines. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TITS.2022.3182371 | IEEE Transactions on Intelligent Transportation Systems |
Keywords | DocType | Volume |
Rail fault text,named entity recognition,adversarial training,lattice LSTM | Journal | 23 |
Issue | ISSN | Citations |
11 | 1524-9050 | 1 |
PageRank | References | Authors |
0.37 | 12 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuai Su | 1 | 12 | 1.52 |
Jia Qu | 2 | 1 | 2.06 |
Yuan Cao | 3 | 73 | 10.39 |
Ruoqing Li | 4 | 1 | 0.37 |
Guang Wang | 5 | 1 | 0.37 |