2026
- Master's Thesis: Investigating Psycholinguistically-inspired Training Losses for Human Reading Time Prediction with Transformers
- Lukas Mielczarek and Laura Kallmeyer (2026). Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal. Proceedings of CMCL@LREC.
2025
- Lukas Mielczarek, Timothée Bernard, Laura Kallmeyer, Katharina Spalek and Benoit Crabbé (2025). Modelling Expectation-based and Memory-based Predictors of Human Reading Times with Syntax-guided Attention. Proceedings of BriGap-2.
- Seminar paper: Lukas Mielczarek. Psycholinguistically Motivated Tree-Adjoining Grammar.
2024
- Preliminary work: Lukas Mielczarek, Laura Kallmeyer, Hassan Sajjad, Katharina Spalek. Does syntactic parsing improve eye tracking prediction? Code available here .
- Seminar paper: Lukas Mielczarek, Linbo Zhang Static Word Embeddings.
2023
- Bachelor's thesis: Integrating Supertag Features into Neural Discontinuous Constituent Parsing.
2020
- Seminar paper: A finite-state morphological grammar of Wymysorys.
English (UK) 
Deutsch