
Michelle Wastl, M.A.
- PhD candidate
- Text Technology
Header
I am a PhD candidate in Computational Linguistics working on theInvestigaDiff project, where I am looking into how semantic differences can be automatically detected across documents in different languages. It is a pleasure to be supervised by Prof. Dr. Rico Sennrich, Dr. Jannis Vamvas, and Prof. Dr. Sarah Ebling.
I hold a master's degree in Computational Linguistics and the interdisciplinary program Methods – Data – Society. For my master's thesis, I worked on unsupervised translation direction detection, which was recognized with the UZH semester award. Prior to that, I completed my bachelor's degree in German Literature and Linguistics, and Comparative Linguistics.
Michelle Wastl; Jannis Vamvas; Rico Sennrich (2025).
Machine Translation Models are Zero-Shot Detectors of Translation Direction
In Findings of the Association for Computational Linguistics: ACL 2025. Vienna, Austria, pp. 1054–1074. [code] [demo]
Michelle Wastl; Jannis Vamvas; Rico Sennrich (2025).UZH at SemEval-2025 Task 3: Token-Level Self-Consistency for Hallucination Detection
In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025). Vienna, Austria, pp. 257-270. [code]
Michelle Wastl; Jannis Vamvas; Selena Calleri; Rico Sennrich (2025).
20min-XD: A Comparable Corpus of Swiss News Articles
In Proceedings of the 10th edition of the Swiss Text Analytics Conference. Winterthur, Switzerland. [code] [data]
★ best paper award
Selena Calleri; Michelle Wastl; Bojan Perić; Andreas Abegg (2024).
Interlex–A search engine to explore the interconnectedness of Swiss legal texts
Proceedings of the 9th edition of the Swiss Text Analytics Conference. Chur, Switzerland, pp. 174-174.