Hong Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hong Shen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Fei Min
Institute of Electronics, Chinese Academy of Sciences, Suzhou, China
1 shared publication- Kangrong Jin
Institute of Electronics, Chinese Academy of Sciences, Suzhou, China
1 shared publication Long-Kun Yu
Key Laboratory of Atmospheric Composition and Optical Radiation, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Anhui Hefei 230031, China
1 shared publication- Wuling Liu
GSIS Department, Suzhou Aerospace Information Research Institute, Suzhou, China
1 shared publication Xu Jing
Key Laboratory of Atmospheric Composition and Optical Radiation, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Anhui Hefei 230031, China
1 shared publication- Xue Qiao
Institute of Electronics, Chinese Academy of Sciences, Suzhou, China
1 shared publication
Latest Publications
- Open Access
- 4 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 81575-81587
A Graph Convolutional Network With Multiple Dependency Representations for Relation Extraction
Dependency analysis can assist neural networks to capture semantic features within a sentence for entity relation extraction (RE). Both hard and soft strategies of encoding dependency tree structure have been developed to balance the beneficial extra information against the unfavorable interference in the task of RE. A wide application of graph convolutional network (GCN) in the field of natural language processing (NLP) has demonstrated its effectiveness in encoding the input sentence with the dependency tree structure, as well as its efficiency in parallel computation. This study proposes a novel GCN-based model using multiple representations to depict the dependency tree from various perspectives, and combines those dependency representations afterward to obtain a better sentence representation for relation classification. This model can maximally draw from the sentence the semantic features relevant to the relationship between entities. Results show that our model achieves state-of-the-art performance in terms of the F 1 score (68.0) on the Text Analysis Conference relation extraction dataset (TACRED). In addition, we verify that the renormalization parameter in the GCN operation should be carefully chosen to help GCN-based models achieve its best performance.
- 4 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 81575-81587
Open AccessA Graph Convolutional Network With Multiple Dependency Representations for Relation Extraction
Dependency analysis can assist neural networks to capture semantic features within a sentence for entity relation extraction (RE). Both hard and soft strategies of encoding dependency tree structure have been developed to balance the beneficial extra information against the unfavorable interference in the task of RE. A wide application of graph convolutional network (GCN) in the field of natural language processing (NLP) has demonstrated its effectiveness in encoding the input sentence with the dependency tree structure, as well as its efficiency in parallel computation. This study proposes a novel GCN-based model using multiple representations to depict the dependency tree from various perspectives, and combines those dependency representations afterward to obtain a better sentence representation for relation classification. This model can maximally draw from the sentence the semantic features relevant to the relationship between entities. Results show that our model achieves state-of-the-art performance in terms of the F 1 score (68.0) on the Text Analysis Conference relation extraction dataset (TACRED). In addition, we verify that the renormalization parameter in the GCN operation should be carefully chosen to help GCN-based models achieve its best performance.
- 5 February 2014
- Published by Optica Publishing Group in Optics Letters
- Vol. 39 (4) , 789-792
Isoplanatic angle in finite distance: theory analysis on measurement feasibility
Previous studies have shown that the isoplanatic angle () can be measured by using plane-wave scintillation. The problem of measuring the isoplanatic angle in a finite distance using spherical-wave scintillation is considered in this Letter. Based on theoretical analysis and numerical evaluation, we found that by selecting suitable aperture size and aperture separations, the isoplanatic angle can be estimated through spherical-wave scintillation and covariance of irradiance in three received apertures using a point source. The error of measured by this method is less than 6% in typical turbulence models.- 5 February 2014
- Published by Optica Publishing Group in Optics Letters
- Vol. 39 (4) , 789-792
Isoplanatic angle in finite distance: theory analysis on measurement feasibility
Previous studies have shown that the isoplanatic angle () can be measured by using plane-wave scintillation. The problem of measuring the isoplanatic angle in a finite distance using spherical-wave scintillation is considered in this Letter. Based on theoretical analysis and numerical evaluation, we found that by selecting suitable aperture size and aperture separations, the isoplanatic angle can be estimated through spherical-wave scintillation and covariance of irradiance in three received apertures using a point source. The error of measured by this method is less than 6% in typical turbulence models.