Simon Yu

Simon Yu

MRes Student at NLP and AI

University of Edinburgh

Biography

Hi! I’m Simon Yu, a MSc (By Research) student at the Institute of Language, Cognition and Computation at University of Edinburgh, supervised by Jeff Z. Pan. Prior to my graduate study, I received my bachelor’s degree from the University of Edinburgh with First Class Honours and was awarded the Outstanding Dissertation, supervised by Jacques Fleuriot. My bachelor’s degree was fully funded by the Macao Foundation Undergraduate Scholarship, and I was among the top 1% of students in my A-level course.

My research interests primarily lie in Deep Learning and Natural Language Processing, with the goal of building robust systems that are invulnerable to attack. My research spans a focus on commonsense QA and contrastive learning on graph-structured data. I previously spent half a year working as a research intern at Huawei Noah’s Ark Lab, where I mainly focused on entity linking and disambiguation, as well as knowledge graph construction.

Note: I am actively looking for a PhD position starting in the fall of 2024, primarily in the area of Robustness and trustworthy in Large Language Model. Any opportunity would be greatly appreciated, and please feel free to contact me if possible!

Interests
  • Robustness for LLM
  • Cross-Lingual Transfer Learning
  • Representation Learning
Education
  • Master by Research in NLP, 2023-2024

    University of Edinburgh

  • BSc in Artificial Intelligence and Computer Science, 2019-2023

    University of Edinburgh

Experience

 
 
 
 
 
Research Assistant
October 2022 – September 2023 Edinburgh, United Kingdom
 
 
 
 
 
Research Intern
Huawei Edinburgh Noah Arks Lab R&D
March 2022 – September 2022 Edinburgh, United Kingdom
 
 
 
 
 
Embedded Software Engineer
Huawei Cambridge R&D Centre
June 2021 – March 2022 Cambridge, Science Park, UK

Publications

Quickly discover relevant content by filtering publications.
(2023). HJCL: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification. In EMNLP 2023.

PDF Cite Code

(2023). BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering. In ACL 2023.

PDF Cite Slides