Juri Opitz, PhD

Hi there! I’m an engineer and researcher interested in machine learning (“AI”), statistics, NLP (Natural Language Processing), and computational linguistics.

I obtained my doctoral degree (with highest honors) from Heidelberg University, where I was advised by Anette Frank. Now I’m based in Switzerland, working at the University of Zurich’s CL department.

Blog

Check out my blog, where I’m sharing some thought bits from time to time.

Research and Projects

I have first-authored 20+ peer-reviewed research projects, and led several others as supervisor. Most of them are on topics of AI evaluation, interpretability and meaning representations, as well as embeddings and information retrieval.

For an overview of all publications see my Google Scholar Page.

🍄 Some selected works are:

A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice. MIT press, arxiv
Interpretable Text Embeddings and Text Similarity Explanation: A Survey. ACL anthology, arxiv
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features. ACL anthology, arxiv
Natural Language Processing RELIES on Linguistics. MIT press
SMATCH++: Standardized and Extended Evaluation of Semantic Graphs. ACL anthology, arxiv

🖥️ I contribute to opensource projects, see also my github page. For an overview and a few more details of some current research interest, please click here.

Teaching and Supervising

I have taught courses on diverse topics, and supervised Bachelor and Master theses. Please see this page for more information.

Invited talks

I have given invited talks on these topics:

Similar, but why? Studies on Semantic Text Similarity at University of Dusseldorf.
Metrics of meaning representations and their interesting applications (Two talks) 1) at DMR workshop at International Conference for Comp. Semantics, 2023, Nancy, France. 2) AM4AS Workshop at TALN 2025, Marseille.
NLP and linguistics (Three talks) 1) @Text+ Plenary, 2024, Mannheim, Germany. 2) at NLP seminar series at National Research Council, Canada. 3) European Research Network Universality, Diversity, and Originality in Language Technology.