Xuhui Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuhui Song has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Hongtao Yu
National Digital Switching System Engineering & Technological R&D Center, PLA Information Engineering University, Zhengzhou 450002, China
1 shared publication - Huansha Wang
National Digital Switching System Engineering & Technological R&D Center, PLA Information Engineering University, Zhengzhou 450001, China
1 shared publication - Shaomei Li
Information Technology Institute, Information Engineering University, Zhengzhou 450001, China
1 shared publication
Latest Publications
- Open Access
- 22 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (3) , 569
Robust Chinese Named Entity Recognition Based on Fusion Graph Embedding
Named entity recognition is an important basic task in the field of natural language processing. The current mainstream named entity recognition methods are mainly based on the deep neural network model. The vulnerability of the deep neural network itself leads to a significant decline in the accuracy of named entity recognition when there is adversarial text in the text. In order to improve the robustness of named entity recognition under adversarial conditions, this paper proposes a Chinese named entity recognition model based on fusion graph embedding. Firstly, the model encodes and represents the phonetic and glyph information of the input text through graph learning and integrates above-multimodal knowledge into the model, thus enhancing the robustness of the model. Secondly, we use the Bi-LSTM to further obtain the context information of the text. Finally, conditional random field is used to decode and label entities. The experimental results on OntoNotes4.0, MSRA, Weibo, and Resume datasets show that the F1 values of this model increased by 3.76%, 3.93%, 4.16%, and 6.49%, respectively, in the presence of adversarial text, which verifies the effectiveness of this model.
- 22 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (3) , 569
Open AccessRobust Chinese Named Entity Recognition Based on Fusion Graph Embedding
Named entity recognition is an important basic task in the field of natural language processing. The current mainstream named entity recognition methods are mainly based on the deep neural network model. The vulnerability of the deep neural network itself leads to a significant decline in the accuracy of named entity recognition when there is adversarial text in the text. In order to improve the robustness of named entity recognition under adversarial conditions, this paper proposes a Chinese named entity recognition model based on fusion graph embedding. Firstly, the model encodes and represents the phonetic and glyph information of the input text through graph learning and integrates above-multimodal knowledge into the model, thus enhancing the robustness of the model. Secondly, we use the Bi-LSTM to further obtain the context information of the text. Finally, conditional random field is used to decode and label entities. The experimental results on OntoNotes4.0, MSRA, Weibo, and Resume datasets show that the F1 values of this model increased by 3.76%, 3.93%, 4.16%, and 6.49%, respectively, in the presence of adversarial text, which verifies the effectiveness of this model.