My primary research interests lie in the area of neural-symbolic AI, especially knowledge representation (KR) and natural language processing (NLP). In my PhD (DPhil), I have been working on adapting language models (LMs) to a range of ontology engineering tasks including ontology alignment, completion, embeddings, and more. I am also interested in geometric embeddings and their use in addressing the limitations of LMs and representing logics.
I have been actively developing and maintaining DeepOnto, a Python package for ontology engineering with deep learning and particularly LMs.
Before my PhD, I took my undergraduate study at the University of Edinburgh and attained the best performance prize for the BSc (Hons) AI & Maths degree. My final year project supervised by Dr Shay B. Cohen has led to a publication about machine transliteration.
Please refer to my page at https://www.yuanhe.wiki/ for more information.
BERTMap: A BERT−based Ontology Alignment System
Yuan He‚ Jiaoyan Chen‚ Denvar Antonyrajah and Ian Horrocks
In Proceedings of 36th AAAI Conference on Artificial Intelligence 2022 (AAAI−2022). 2022.
Machine Learning−Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching
Yuan He‚ Jiaoyan Chen‚ Hang Dong‚ Ernesto Jiménez−Ruiz‚ Ali Hadian and Ian Horrocks
In The 21st International Semantic Web Conference (ISWC−2022). 2022.
Best Resource Paper Candidate
Language Model Analysis for Ontology Subsumption Inferece
Yuan He‚ Jiaoyan Chen‚ Ernesto‚ Jiménez−Ruiz‚ Hang Dong and Ian Horrocks
In Findings of the Association for Computational Linguistics: ACL 2023. 2023.