CV
You can download my full resumé here: Download PDF
Education
- Ph.D in Computer Science, National University of Singapore, 2020 - Present
- Advisor: Prof. Min-Yen Kan
- Research Focus: Data-to-Text Generation, Financial NLP
- Master of Computing, National University of Singapore, 2017 - 2018
- BEng in Electrical and Electronics Engineering, Nanyang Technological University, 2011 - 2015
Work Experience
- Data Science - Specialist, Jun 2020 – Present
- Rio Tinto, Singapore
- Lead client-facing data science projects for different Rio Tinto entity
- Provide mentorship and coaching to the intern data scientists on technical skillset and innovative data science critical thinking
- Data Scientist, Aug 2018 – May 2020
- Rio Tinto, Singapore
- Design and continually improve services that solve business problems
- Provide insight to making improved decisions for various business functions
- Data Scientist Intern, Jan 2018 – Apr 2018
- Teralytics, Singapore
- Provide support for big data projects development
- Design and develop model evaluation scripts, analyze and present evaluation results
Research Interests
- Data-to-text Generation
- Document Summarization
- Information Retrieval
- Financial NLP
- Natural Language Generation with Large Language Models
Skills
- Programming Languages: Python, R, SQL
- Machine Learning & NLP
- Natural Language Generation
- Large Language Models
- Deep Learning (PyTorch, TensorFlow)
- Data-to-Text Systems
- Data Science
- Statistical Analysis
- Data Visualization
- Predictive Modeling
Publications
Yang, Yajing, Tony Deng, and Min-Yen Kan. (2025). "KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration." Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China.
Yang, Yajing, Qian Liu, and Min-Yen Kan. (2024). "DataTales: A Benchmark for Real-World Intelligent Data Narration." Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA.
Kashyap, Abhinav Ramesh, Yajing Yang, and Min-Yen Kan. (2023). "Scientific document processing: challenges for modern learning methods." International Journal on Digital Libraries. 24, 283–309.
