Philipp Scharpf
Doctoral Researcher
RESEARCH STORY
During my master’s thesis research in physics on the topic “Simulation and Visualization of Gravitational Waves from Binary Black Holes” at the University of Konstanz, I realized the current need for effective tools to process mathematical formulas in document analysis and Mathematical Information Retrieval (MathIR).
Since then, I review, develop, and evaluate Mathematical Entity Linking (MathEL) methods and applications. Methods include STEM document (formula & identifier) annotation recommendation, formula concept retrieval (classification & clustering), and nearest-neighbor retrieval. Applications include mathematical (STEM) document classification & clustering, Wikipage readability & accessibility, formula search, question answering, and question generation. Particularly, I am focused on the Wikidata knowledge graph.
RESEARCH FIELDS
- Mathematical Information Retrieval (MathIR)
- Mathematical Entity Linking (MathEL)
- Formula search
- Math document classification & clustering
- Question answering
- Question generation
- Recommender systems
- Wikipedia & Wikidata
TEACHING & PROJECTS
The following list illustrates examples of the student projects (see pdf file here). Feel free to contact me if you have interest in any of these or my other research topics.
SELECTED PUBLICATIONS
For a list of my publications see also my profiles on Google Scholar and ResearchGate.
- Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling P. Scharpf, M. Schubotz, and B. Gipp in Proceedings of the ACM/IEEE Joint Conference on Digital Libraries (JCDL) 2022 PDF
- Fast Linking of Mathematical Wikidata Entities in Wikipedia Articles Using Annotation Recommendation
P. Scharpf, M. Schubotz, and B. Gipp
in Companion Proceedings of the Web Conference (WWW) 2021
PDF - Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language
P. Scharpf, M. Schubotz, A. Youssef, F. Hamborg, N. Meuschke, and B. Gipp
in Proceedings of the ACM/IEEE Joint Conference on Digital Libraries (JCDL) 2020
PDF - Introducing MathQA – A Math-Aware Question Answering System
Schubotz, M. Scharpf, P. Gipp, B.
Information Discovery and Delivery Journal (Emerald Publishing) 2018
PDF
SHORT CV
2017 – present
Ph.D. Student
Gipp Lab, University of Konstanz, Wuppertal, and Göttingen
2022 – present
Data and AI Consultant
AI4Future Dataconsulting, Konstanz Germany
2018 – 2021
Data and AI Consultant
BMT Business Meets Technology AG, Bottighofen Switzerland
2019 – 2020
Machine Learning and Information Science Researcher
Chair for Data & Knowledge Engineering, University of Wuppertal
2018 – 2019
Machine Learning and Information Science Researcher
Dept. of Computer and Information Science, University of Konstanz
2017
Physics, M. Sc.
Dept. of Physics, University of Konstanz
2014
Physics, B. Sc.
Dept. of Physics, University of Zürich
