Zheng Hu

Zheng Hu

Auto-generated profile, based on publicly available information

Zheng Hu

Southeast University,School of Computer Science and Engineering,Nanjing,China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
29 November 2023 in Renewable Energy
Verified
Journal Article
Closed access
ZHZheng Hu
Zheng Hu
YCYongping Chen
Yongping Chen
CZChengbin Zhang
Chengbin Zhang

22 May 2023 in Renewable Energy
Verified
Journal Article
Closed access
ZHZheng Hu
Zheng Hu
ZDZilong Deng
Zilong Deng
WGWei Gao
Wei Gao
YCYongping Chen
Yongping Chen

23 December 2025 in Energy Conversion and Management
Verified
Journal Article
Closed access
KZKouer Zhang
Kouer Zhang
XHXiaoyu Huo
Xiaoyu Huo
ZHZheng Hu
Zheng Hu
XZXiao Zhang
Xiao Zhang
LALiang An
Liang An

1 January 2021
Verified
Conference Paper
Open access
PDF file
DZDong Zhang
Dong Zhang
ZHZheng Hu
Zheng Hu
SLShoushan Li
Shoushan Li
HWHanqian Wu
Hanqian Wu
QZQiaoming Zhu
Qiaoming Zhu
GZGuodong Zhou
Guodong Zhou
Dong Zhang, Zheng Hu, Shoushan Li, Hanqian Wu, Qiaoming Zhu, Guodong Zhou. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2021.

20 July 2022
Verified
Conference Paper
Closed access
LLLu Li
Lu Li
ZHZheng Hu
Zheng Hu
BZBaohua Zhao
Baohua Zhao
SWSuzhong Wei
Suzhong Wei
AZAihua Zhou
Aihua Zhou
HWHanqian Wu
Hanqian Wu
As one of the basic tasks in natural language processing (NLP), Chinese word segmentation (CWS) is a necessary and key preprocessing step for many natural language processing tasks. The performance of CWS directly affects the final performance of subsequent tasks. Traditional word segmentation approaches mainly use conditional random field (CRF) decoder and BIO tags for sequence labeling, and the recent mainstream approaches normally employ the pre-trained bidirectional encoder representations from transformers (BERT) model as text encoder. This greatly affects the speed of word segmentation. Different from the existing approaches, this paper proposes a Chinese word segmentation approach based on word boundary classification, which utilizes a lite BERT (ALBERT) model as the text encoder. This approach directly determines whether the position between characters is the boundary between two potential words without using CRF decoding. Experimental results show that our proposed approach can achieve significant improvements, and significantly reduces the training and testing time of CWS.