Wenjuan Han

Wenjuan Han

Auto-generated profile, based on publicly available information

Wenjuan Han

Department of Computer Science, National University of Singapore

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
21 May 2025 in Information Fusion
Verified
Journal Article
Closed access
NCNing Cheng
Ning Cheng
JXJinan Xu
Jinan Xu
CGChanghao Guan
Changhao Guan
JGJing Gao
Jing Gao
WWWeihao Wang
Weihao Wang
WHWenjuan Han
Wenjuan Han

1 January 2020
Verified
Conference Paper
Open access
PDF file
EYErxin Yu
Erxin Yu
WHWenjuan Han
Wenjuan Han
YTYuan Tian
Yuan Tian
YCYi Chang
Yi Chang
Erxin Yu, Wenjuan Han, Yuan Tian, Yi Chang. Proceedings of the 28th International Conference on Computational Linguistics. 2020.

1 July 2019 in Neurocomputing
Verified
Journal Article
Closed access
WHWenjuan Han
Wenjuan Han
YJYong Jiang
Yong Jiang
KTKewei Tu
Kewei Tu

12 April 2019 in IEEE Access
Verified
Journal Article
Open access
WHWenjuan Han
Wenjuan Han
GWGe Wang
Ge Wang
KTKewei Tu
Kewei Tu
Learning to discover hidden variables from unlabeled data is an important task. Traditional generative methods model the generation process of the observed variables as well as the hidden variables. However, tractable inference and learning on these models requires strong conditional independence assumptions being made among observed and hidden variables. To tackle this limitation, we propose an autoencoder framework. The encoder produces an intermediate representation from the observed variables, and the decoder is a generative latent variable model conditioned on the intermediate representation that tries to generate the hidden variables as well as to reconstruct the observed variables. We introduce three variant models of our framework with either a deterministic or a stochastic encoding process. To optimize our model, we propose an algorithm similar to the classic expectation–maximization (EM) algorithm that supports online learning for large-scale datasets. The flexibility of our framework allows us to apply it to various scenarios where the explicit inference of hidden variables is desired. We discuss the applications of our framework to the perceptual grouping task and the part-of-speech (POS) induction task. Our experiments on the two tasks demonstrate that our framework can achieve better performance than vanilla latent variable generative models.

1 January 2021
Verified
Conference Paper
Open access
PDF file
ZZZhang Zhang
Zhang Zhang
GWGe Wang
Ge Wang
WHWenjuan Han
Wenjuan Han
KTKewei Tu
Kewei Tu
Liwen Zhang, Ge Wang, Wenjuan Han, Kewei Tu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

20 January 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
PZPengyu Zhao
Pengyu Zhao
JXJinan Xu
Jinan Xu
NCNing Cheng
Ning Cheng
HHHuiqi Hu
Huiqi Hu
XZXue Zhang
Xue Zhang
WHWenjuan Han
Wenjuan Han