Qiyuan Li

Qiyuan Li

Auto-generated profile, based on publicly available information

Qiyuan Li

School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, Hubei, China; Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan, 430065, Hubei, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
QLQiyuan Li
Qiyuan Li
HLHaijiang Liu
Haijiang Liu
CGCaicai Guo
Caicai Guo
CGChao Gao
Chao Gao
DCDeyu Chen
Deyu Chen
JGJinguang Gu
Jinguang Gu

1 March 2025 in Neurocomputing
Verified
Journal Article
Closed access
QLQiyuan Li
Qiyuan Li
CQChen Qiu
Chen Qiu
HLHaijiang Liu
Haijiang Liu
JGJinguang Gu
Jinguang Gu
DLDan Luo
Dan Luo

21 January 2026 in Neural Networks
Verified
Journal Article
Closed access
DCDeyu Chen
Deyu Chen
CGCaicai Guo
Caicai Guo
QLQiyuan Li
Qiyuan Li
JGJinguang Gu
Jinguang Gu
MXMeiyi Xie
Meiyi Xie
HZHong Zhu
Hong Zhu

13 August 2024
Verified
Conference Paper
Open access
QWQi Wang
Qi Wang
QLQiyuan Li
Qiyuan Li
CGChao Gao
Chao Gao
HLHaijiang Liu
Haijiang Liu
FXFangfang Xu
Fangfang Xu
JGJinguang Gu
Jinguang Gu
The construction of medical knowledge graphs(KGs) structures complex medical data to support precise clinical decision-making and knowledge discovery. A core challenge in building medical KGs is effectively representing and processing complex clinical data. Existing triple-based medical knowledge representation methods often fail to fully capture and express the complexity of the data, particularly when dealing with higher-order relationships involving multiple entities. Additionally, the current "Attribute-Concept-Event" three-layer knowledge organization framework shows limitations in representing procedural knowledge in medical scenarios, falling short of the hierarchical and dynamic requirements of evidence-based medicine. To address these issues, we propose a four-layer medical knowledge organization method based on hypergraph theory. By incorporating hypergraph theory and a narrative layer into the KG, we provide a more flexible and dynamic framework for representing complex clinical information. Based on this approach, we construct a four-layer KG, RJUA-HKG, using real QA clinical data from urology as an example. Experiments show that, compared to traditional KGs, RJUA-HKG significantly reduces relational complexity and retrieval time while accurately capturing changes in diagnostic and treatment procedures.

18 June 2025 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
HLHaijiang Liu
Haijiang Liu
CQChen Qiu
Chen Qiu
QLQiyuan Li
Qiyuan Li
MLMaofu Liu
Maofu Liu
LWLi Wang
Li Wang
JGJinguang Gu
Jinguang Gu
The Cross-lingual Dependency Parsing (XDP) task poses a significant challenge due to the differences in dependency structures between training and testing languages, known as the out-of-distribution (OOD) problem. Our research delved into this issue in the XDP dataset by selecting 43 languages from 22 language families. We found that the primary factor of the OOD problem is the unbalanced length distribution among languages. To address the impact of the OOD problem, we propose deep stable learning for Cross-lingual Dependency Parsing (SL-XDP), which utilizes deep stable learning with a feature fusion module. In detail, we implemented five feature fusion operations for generating comprehensive representations with dependency relations and the deep stable learning algorithm to decorrelate dependency structures with sequence length. Our experiments on Universal Dependencies have demonstrated that SL-XDP can lessen the impact of the OOD problem and improve the model generalization among 21 languages, with a maximum improvement of 18%.