N

NLP

This repository contains code and data for experiments for the paper Vocabulary Shapes Cross-Lingual Variation of Word-Order Learnability in Language Models using controlled synthetic language variants. We pretrain Transformer language models on word-order–perturbed corpora and evaluate the effect of word-order irregularity and vocabulary structure on model surprisal across languages.

🗨 Repository to host our minBert implementation for the course 'Deep Learning for Natural Language Processing' at the University of Göttingen.