About Me
I am completing an MSc in Language Technology at Uppsala University, with a background in Business Analytics and four years of professional experience as a data analyst. My research focuses on multilingual NLP, model adaptation, and reliable language technology. My work includes a first-author EAMT 2026 publication on LoRA-based low-resource machine translation, as well as research on modular Mixture-of-Experts, training-data attribution, and evidence-grounded retrieval over long documents. My broader goal is to develop adaptable and reliable NLP systems and to understand how training data and system design shape model behaviour.
Publications
I currently have one peer-reviewed publication, and I’m working on several other manuscripts that are either under review or still in preparation. You can find them all here, with links to the related project pages if you’d like to learn more about the research behind each paper.
LoRA Fine-Tuning of English-Norwegian NMT for the Oil & Gas Industry
Xiaojing Yang, Zhihan Li, Gege Sun, Mengyue Li, Meriem Beloucif
EAMT 2026 research on LoRA adaptation for low-resource petroleum-domain machine translation.
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
First author; lead experimental contributor
Modular Expert Architectures for Multilingual Domain Adaptation: Parameter-Efficient Norwegian Petroleum Translation with LoRA and Gated Routing
Xiaojing Yang
Master's thesis presenting a parameter-efficient multilingual adaptation framework that combines language-specific LoRA experts, gated routing, and target-anchored synthetic data for Norwegian petroleum-domain translation.
MSc Thesis, Uppsala University, 46 pages
Thesis author; framework design and experimental lead
Beyond Routing: Diagnosing Modular LoRA Experts for Low-Resource Multilingual Petroleum-Domain Translation
Xiaojing Yang, Zhihan Li, Meriem Beloucif
A diagnostic study of modular LoRA experts for low-resource petroleum translation.
COLING 2027 via ACL Rolling Review (ARR)
First author; framework design and experimental lead
Projects
I have hands-on experience taking projects from idea and experimentation to implementation and evaluation, covering both research projects and applied AI systems.
Beyond Routing: Diagnosing Modular LoRA Experts for Low-Resource Multilingual Petroleum-Domain Translation
A diagnostic study of modular LoRA experts for low-resource petroleum translation.
Experience
Research, work, and teaching experience across AI, NLP, data analysis, and machine learning.
Research Projects in Language Technology
Designed and led research projects across multilingual NLP, machine translation, retrieval, data attribution, and bias evaluation.
Data Analyst
Completed various data analytics projects spanning customer intelligence, sales optimization, and predictive modeling across e-commerce, retail, and marketing domains.
Teaching Assistant, Machine Translation
Supported 25 students across assignment marking, lab sessions, and project supervision in a machine translation course.
Skills
My technical background connects data analysis, machine learning, NLP research, rigorous evaluation, and research engineering for applied AI systems.
Data Analysis & Visualization
Statistical analysis, exploratory data work, and visualization for real-world datasets, experimental results, and decision support.
AI & Machine Learning
Deep learning, Transformer adaptation, fine-tuning workflows, and model evaluation for research and applied AI systems.
NLP & Language Technology
Multilingual NLP, machine translation, retrieval, and language-technology systems for specialized domains.
Responsible AI & Evaluation
Bias evaluation, human validation, statistical testing, and model behavior analysis for social and linguistic AI risks.