CV

You can download my CV_Chinese version and CV_English version in PDF.

Education

B.S. in Information Management and Information System, Beijing Normal University, Zhuhai (BNUZ), Sept. 2018 - July. 2022
M.S. in Data Science with specialization in Computational Lingustics, University of Macau (UM), Aug. 2022 - July. 2024
Ph.D. student in Computer Science, University of Macau (UM), Aug. 2024 - Present

Work experience

Research Assistant(Full-time): Jan. 2022 - July. 2022
- School of Management, Beijing Normal University, Zhuhai, Zhuhai, China
- Conducted research on the intelligent question answering system in the history of modern Chinese revolution, and completed the construction of the V1.0 version
- Conduct research on text mining and classification of BillBill community bullet chatter. I am mainly responsible for the position detection research, experimental implementation and model comparison of BillBill’s bullet chat text.
Development Intern(Full-time): July 2021 - Jan. 2022
- Orient Overseas Container Line (China) Ltd. Zhuhai, China
- Participate in the maintenance and development of the service background and front-end interface of the OOCL shipping logistics system My OOCL Center (MOC), etc., mainly responsible for the shipping order function module; support and repair the needs and feedback bugs of customers and business departments (technology stack: J2EE, JSP , Oracle, WebLogic, Apache Ant)
- Participated in the reconstruction and development of OOCL container equipment transfer order system (EIR); (technical stack: Vue, SpringBoot, Oracle, Hibernate)

Research experience

Construction of a digital library for the history of modern China’s revolution based on knowledge graph : Worked as Project Manager – May 2019 - March 2021
- Project leader, responsible for project direction control, task assignment, thesis writing and system maintenance and improvement, and the final project is successfully concluded (project management, teamwork)
- Presided over the design of ontology database and knowledge storage structure, knowledge extraction and crawler, knowledge reasoning completion scheme design (ontology research, knowledge engineering)
- Design and development of the Python operation library AutoProtégé for the ontology editing tool Protégé (https://github.com/junchaoIU/AutoProtege)
- Responsible for the front-end development and back-end development of the system, has been deployed and launched (https://gzknowledge.cn) and registered the computer software copyright certificate: China Modern Revolution History Knowledge Graph System V1.0 (the first copyright holder) (Technology stack: React, SpringBoot, Jena)
- Completed the design and application of the information double-layer retrieval model. The paper “The Canton Canon” Digital Library Based on Knowledge Graph - Taking the Revolutionary Archives of Canton in the Republic of China as an Example was published in IEEE 10th International Conference on Educational and Information Technology (ICEIT), was invited to present at the conference to give a report and won the Best Oral Presentation Award of the conference (First author, EI)
- Completed the design and application of the spatiotemporal knowledge model.The paper “Research and application of digitization of Chinese modern revolutionary historical document resources based on spatio-temporal evolution knowledge graph” was under review by the chinese core journal Digital Library Forum (CSSCI).
Research and Application of Digitalization of Long March Red Cultural Resources Based on Knowledge Graph : Worked as Backend Engineer – May 2020 - Present
- Responsible for App back-end technology selection, design and development (technology stack: Flask, Neo4j)
- Participate in the design and construction of the underlying knowledge graph model, the cleaning, transformation and knowledge base storage of structured data (knowledge engineering)
- The project achievement paper “Long March Red Digital Cultural Resource Knowledge Graph Service Mode for Youth Education” was published in the 2021 Lingnan Academic Forum “Youth Red Culture Education Practice and Innovation” thematic collection, and was invited to become a member of the Guangdong Red Culture Research Association
- The paper “Research and application of digitization of Long March Red Cultural Resources Based on Knowledge Graph” was published in Electronic Technology & Software Engineering
Research on text mining and cultural phenomenon based on bullet screen corpus : Worked as Data Mining & Algorithm Engineer – May 2020 - Present
- Participate in data engineering such as barrage crawler, data cleaning and storage; project database barrage data volume reaches 50 million (Python crawler and text preprocessing)
- Responsible for text mining and text classification research of bullet screen corpus, including sentiment analysis and text position detection (using rules, statistical machine learning and deep learning methods)
- Conducted research on new word discovery algorithms in the field of barrage corpus. The paper “Multi-feature fusion new word discovery model for barrage” was under review by the chinese core journal Computer Application Research.
- Conducted research on the construction and application of subculture barrage corpus, and the paper “Construction and Analysis of Subculture Barrage Corpus” has been accepted by journal Information Research

Publications

2024

DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

Junchao Wu , Runzhe Zhan, Derek F. Wong*, Shu Yang, Xinyi Yang, Yulin Yuan, Lidia S. Chao

NeurIPS (Datasets and Benchmarks Track) 2024

[PAPER] [CODE]

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore

Junchao Wu , Runzhe Zhan, Derek F. Wong*, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang

Preprint 2024

[PAPER] [CODE]

2023

A Survey on LLM-generated Text Detection: Necessity, Methods, and Future Directions

Junchao Wu , Shu Yang, Runzhe Zhan, Yulin Yuan*, Derek F. Wong*, Lidia S. Chao

Preprint 2023

[PAPER] [CODE]

Human-in-the-loop Machine Translation with Large Language Model

Xinyi Yang, Runzhe Zhan, Derek F. Wong*, Junchao Wu , Lidia S. Chao

Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track 2023

[PAPER] [CODE]

A Hybrid Medium and Long-Term Relative Humidity Point and Interval Prediction Method for Intensive Poultry Farming

Hang Yin *, Zeyu Wu, Junchao Wu , Junjie Jiang, Yalin Chen, Mingxuan Chen, Shixuan Luo, Lijun Gao *

Mathematics 2023

[PAPER] [CODE]

A Multistep Interval Prediction Method Combining Environmental Variables and Attention Mechanism for Egg Production Rate

Hang Yin *, Zeyu Wu, Junchao Wu , Yalin Chen, Mingxuan Chen, Shixuan Luo, Lijun Gao, Shahbaz Gul Hassan *

Agriculture 2023

[PAPER] [CODE]

2022

The Topic Evolution of Danmaku Text Based on BTM – Taking the Context of COVID-19 as an Example

Xin Chen, Yixin Zhang, Junchao Wu , Lingyu Guo, Jiaxuan Chen and Jing Yang

BDAI（2022 IEEE the 6th International Conference on Big Data and Artificial Intelligence）2022 2022

[PAPER] [CODE]

Best Oral Presentation Award

多特征融合的弹幕新词发现模型(A New Word Discovery Model for Screen-bullet based on fusion of Multiple Features)

Jing Yang*, Xin Chen, Junchao Wu , Lingyu Guo, Jiaxuan Chen and Daoming Lai

计算机应用研究（Computer Application Research） 2022

[PAPER] [CODE]

历时弹幕语料库的构建与探析——以青年亚文化弹幕为例(Construction and Analysis of Diachronic Bullet Corpus——Taking Youth Subculture Bullet as an Example)

Xin Chen, Yixin Zhang, Junchao Wu , Lingyu Guo, Zehui Yu and Jing Yang*

情报探索（Information Research） 2022

[PAPER] [CODE]

基于知识图谱的长征红色文化资源数字化研究与应用(Research and Application of Digitalization of Long March Red Cultural Resources Based on Knowledge Graph)

Lingyu Guo*, Junchao Wu , Xin Chen, Ying Jiang and Zhizhu Geng

电子技术与软件工程（Electronic Technology and Software Engineering） 2022

[PAPER] [CODE]

2021

“The Canton Canon” Digital Library Based on Knowledge Graph - Taking the Revolutionary Archives of Canton in the Republic of China as an Example

Junchao Wu *, Ying Jiang, Xin Chen, Lingyu Guo, Xiaotong Wei and Xiaoyan Yang

ICEIT（2021 IEEE 10th International Conference on Educational and Information Technology）2021 2021

[PAPER] [CODE]

Best Presentation Award

Awards

Outstanding graduate of Beijing Normal University,Zhuhai, 2022
The Outstanding Graduation Thesis of Beijing Normal University, Zhuhai, 2022
Professional Scholarship of Beijing Normal University, Zhuhai, 2019, 2020, 2021
Academic Scholarship of Beijing Normal University, Zhuhai, 2021
Outstanding student cadre Honor of Beijing Normal University, Zhuhai, 2019, 2020
National Second Prize & Guangdong First Prize in the 7th Teddy Cup Data Mining Challenge (Title: Analysis of Safe Driving Behavior of Transport Vehicles), 2019
First Prize in China University Students Mathematical Contest in Modeling, Guangdong Division (Title: Credit Decisions of Small, Medium and Micro Enterprises), 2020
Best Presentation Award in the 10th IEEE International Conference on Education and Information Technology, ICEIT 2021
Third Prize in the 8th “Challenge Cup” College Students’ Extracurricular Academic Science and Technology Works Competition in Beijing Normal University, Zhuhai, 2020
Third Prize in the 2nd Guangdong-Hong Kong-Macau College Student Public Administration Data Analysis Contest, 2022

Professional skills

English Level: IELTS(6.5), CET-6(507)
Programming Languages: C, Python, JAVA, JavaScript, SQL, Bash
Development Frameworks: SpringBoot, React.js, Flask
Deep Learning Tools: Scikit-learn, PyTorch, Keras, Fairseq, Transformers
DB Tools: Neo4j, MySQL, Oracle DB
Other Tools: WebLogic, Apache Ant, Jena, Git, Hanlp, Echart
Soft Skills: Leadership, Event Management, Writing, Public Speaking, Time Management