Cangzhi Zheng

Cangzhi Zheng

Auto-generated profile, based on publicly available information

Cangzhi Zheng

School of Computer Engineering and Science Shanghai University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
25 March 2023 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
QXQianqian Xu
Qianqian Xu
JPJunjie Peng
Junjie Peng
CZCangzhi Zheng
Cangzhi Zheng
STShuhua Tan
Shuhua Tan
FYFen Yi
Fen Yi
FCFeng Cheng
Feng Cheng
As a common language form in oral communication, short text is hard to be used in the applications such as intent understanding, text classification and so on due to its limited content and information, as well as irregular expression and missing components. To increase the availability of short texts in real applications, we propose a Label Information Assisting-based Model (LIAM) for Chinese short text classification. In the model, we jointly use sentence-level features and word-level features to reduce text information loss. And the sentence-level features are fused with relevant label information by the Label Information Extending and Fusion (LIEF) module while the word-level features are also enhanced with assistance of relevant label information. By utilizing the text-related information from labels as extended information, the model enriches and enhances the features of short text, benefiting classification. To verify the correctness and effectiveness of the proposed method, we conduct extensive experiments on four Chinese datasets and six sub-datasets with different models. The experimental results show that LIAM presented can effectively enrich information for text and much improve the performance of short text classification. It performs much better than other methods do. What is more, the less the training set, the greater the advantages of the model.

23 August 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
CZCangzhi Zheng
Cangzhi Zheng
JPJunjie Peng
Junjie Peng
LWLan Wang
Lan Wang
LZLi’aN Zhu
Li’aN Zhu
JGJiatao Guo
Jiatao Guo
ZCZesu Cai
Zesu Cai

1 January 2025
Verified
Conference Paper
Open access
PDF file
YJYijie Jin
Yijie Jin
JPJunjie Peng
Junjie Peng
XLXuanchao Lin
Xuanchao Lin
HYHaochen Yuan
Haochen Yuan
LWLan Wang
Lan Wang
CZCangzhi Zheng
Cangzhi Zheng
Yijie Jin, Junjie Peng, Xuanchao Lin, Haochen Yuan, Lan Wang, Cangzhi Zheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

14 August 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
CZCangzhi Zheng
Cangzhi Zheng
JPJunjie Peng
Junjie Peng
ZCZesu Cai
Zesu Cai

2 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
YJYijie Jin
Yijie Jin
JPJunjie Peng
Junjie Peng
XLXuanchao Lin
Xuanchao Lin
HYHaochen Yuan
Haochen Yuan
LWLan Wang
Lan Wang
CZCangzhi Zheng
Cangzhi Zheng
Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments, and existing models have made significant progress in this area. The central challenge in MSA is multimodal fusion, which is predominantly addressed by Multimodal Transformers (MulTs). Although act as the paradigm, MulTs suffer from efficiency concerns. In this work, from the perspective of efficiency optimization, we propose and prove that MulTs are hierarchical modal-wise heterogeneous graphs (HMHGs), and we introduce the graph-structured representation pattern of MulTs. Based on this pattern, we propose an Interlaced Mask (IM) mechanism to design the Graph-Structured and Interlaced-Masked Multimodal Transformer (GsiT). It is formally equivalent to MulTs which achieves an efficient weight-sharing mechanism without information disorder through IM, enabling All-Modal-In-One fusion with only 1/3 of the parameters of pure MulTs. A Triton kernel called Decomposition is implemented to ensure avoiding additional computational overhead. Moreover, it achieves significantly higher performance than traditional MulTs. To further validate the effectiveness of GsiT itself and the HMHG concept, we integrate them into multiple state-of-the-art models and demonstrate notable performance improvements and parameter reduction on widely used MSA datasets.