Zijian Huang

Zijian Huang

Auto-generated profile, based on publicly available information

Zijian Huang

Wuhan Textile University,China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
30 June 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
KLKangsheng Li
Kangsheng Li
XGXin Gao
Xin Gao
SFShiyuan Fu
Shiyuan Fu
XDXinping Diao
Xinping Diao
PYPing Ye
Ping Ye
ZHZijian Huang
Zijian Huang

11 February 2022 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
KLKangsheng Li
Kangsheng Li
XGXin Gao
Xin Gao
XJXin Jia
Xin Jia
BXBing Xue
Bing Xue
SFShiyuan Fu
Shiyuan Fu
ZHZijian Huang
Zijian Huang

17 October 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
XGXin Gao
Xin Gao
JYJiahao Yu
Jiahao Yu
SZSen Zha
Sen Zha
SFShiyuan Fu
Shiyuan Fu
BXBing Xue
Bing Xue
GZGuangyao Zhang
Guangyao Zhang

13 May 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
XGXin Gao
Xin Gao
XJXin Jia
Xin Jia
JLJing Liu
Jing Liu
BXBing Xue
Bing Xue
ZHZijian Huang
Zijian Huang
KLKangsheng Li
Kangsheng Li

11 March 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
ZLZhiyu Liu
Zhiyu Liu
XGXin Gao
Xin Gao
XJXin Jia
Xin Jia
Bing XueBing Xue
Bing Xue
SFShiyuan Fu
Shiyuan Fu
ZHZijian Huang
Zijian Huang

28 August 2023
Verified
Conference Paper
Closed access
XYXun Yao
Xun Yao
ZHZijian Huang
Zijian Huang
JMJunlong Ma
Junlong Ma
JCJingxue Chen
Jingxue Chen
JACK YANGJACK YANG
JACK YANG
Multiple Choice Question Answering (MCQA) is a well-established task in the field of Machine Reading Comprehension (MRC). Its objective is to identify the correct answer from a given set of options, based on the provided background passage and question. Recent advancements in large-scale Pre-trained Language Models (PLMs) have yielded impressive performance in MCQA. However, achieving such performance requires a significant number of training samples, leading to time-consuming and labor-intensive sample acquisition and annotation processes. To overcome the limitation posed by the availability of training samples, this paper explores the potential of leveraging the [Mask] token, which is commonly used in Masked Language Modeling (MLM) during the self-supervised training of PLMs. Specifically, the paper introduces a straightforward yet effective approach called [Mask] based Data Augmentation (MDA). The proposed method involves injecting [Mask] tokens into background passages to create masked versions of the original data. Moreover, a self-evaluator is introduced to regulate the process of masking production, with the objective of minimizing negative impact caused by argumentation noise. The effectiveness of the proposed method is empirically validated using various benchmark MCQA datasets. Experimental results demonstrate considerable improvements over state-of-the-arts.