Qi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qi Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Pengcheng Guo
SCHOOL OF SOFTWARE ENGINEERING, Xi'an Jiaotong University, China, Xi'an, China
2 shared publications - Yonghong Song
Xi’an Jiaotong University
2 shared publications - Boyu Wang
Western University
1 shared publication - Jiahao Liu
School of Software Engineering, Xian Jiaotong University, Xian, China
1 shared publication - Yangyang Hui
Xi An Jiao Tong Univ, Sch Software Engn, 28 Xianning West Rd, Xian 710049, Shaanxi, Peoples R China
1 shared publication
Latest Publications
- 16 November 2024
- Published by Elsevier in Neurocomputing
- Vol. 616
CRMSP: A semi-supervised approach for key information extraction with Class-Rebalancing and Merged Semantic Pseudo-Labeling
- 16 November 2024
- Published by Elsevier in Neurocomputing
- Vol. 616
CRMSP: A semi-supervised approach for key information extraction with Class-Rebalancing and Merged Semantic Pseudo-Labeling
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 9025-9036
PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification
Document key information extraction (DKIE) methods often require a large number of labeled samples, imposing substantial annotation costs in practical scenarios. Fortunately, pseudo-labeling based semi-supervised learning (PSSL) algorithms provide an effective paradigm to alleviate the reliance on labeled data by leveraging unlabeled data. However, the main challenges for PSSL in DKIE tasks: 1) context dependency of DKIE results in incorrect pseudo-labels. 2) high intra-class variance and low inter-class variation on DKIE. To this end, this paper proposes a similarity matrix Pseudo-Label Bias Rectification (PLBR) semi-supervised method for DKIE tasks, which improves the quality of pseudo-labels on DKIE benchmarks with rare labels. More specifically, the Similarity Matrix Bias Rectification (SMBR) module is proposed to improve the quality of pseudolabels, which utilizes the contextual information of DKIE data through the analysis of similarity between labeled and unlabeled data. Moreover, a dual branch adaptive alignment (DBAA) mechanism is designed to adaptively align intra-class variance and alleviate inter-class variation on DKIE benchmarks, which is composed of two adaptive alignment ways. One is the intra-class alignment branch, which is designed to adaptively align intraclass variance. The other one is the inter-class alignment branch, which is developed to adaptively alleviate inter-class variance changes on the representation level. Extensive experiment results on two benchmarks demonstrate that PLBR achieves state-ofthe-art performance and its performance surpasses the previous SOTA by 2.11% ∼ 2.53%, 2.09% ∼ 2.49% F1-score on FUNSD and CORD with rare labeled samples, respectively. Code will be open to the public
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 9025-9036
PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification
Document key information extraction (DKIE) methods often require a large number of labeled samples, imposing substantial annotation costs in practical scenarios. Fortunately, pseudo-labeling based semi-supervised learning (PSSL) algorithms provide an effective paradigm to alleviate the reliance on labeled data by leveraging unlabeled data. However, the main challenges for PSSL in DKIE tasks: 1) context dependency of DKIE results in incorrect pseudo-labels. 2) high intra-class variance and low inter-class variation on DKIE. To this end, this paper proposes a similarity matrix Pseudo-Label Bias Rectification (PLBR) semi-supervised method for DKIE tasks, which improves the quality of pseudo-labels on DKIE benchmarks with rare labels. More specifically, the Similarity Matrix Bias Rectification (SMBR) module is proposed to improve the quality of pseudolabels, which utilizes the contextual information of DKIE data through the analysis of similarity between labeled and unlabeled data. Moreover, a dual branch adaptive alignment (DBAA) mechanism is designed to adaptively align intra-class variance and alleviate inter-class variation on DKIE benchmarks, which is composed of two adaptive alignment ways. One is the intra-class alignment branch, which is designed to adaptively align intraclass variance. The other one is the inter-class alignment branch, which is developed to adaptively alleviate inter-class variance changes on the representation level. Extensive experiment results on two benchmarks demonstrate that PLBR achieves state-ofthe-art performance and its performance surpasses the previous SOTA by 2.11% ∼ 2.53%, 2.09% ∼ 2.49% F1-score on FUNSD and CORD with rare labeled samples, respectively. Code will be open to the public