mate Collection Grammar Error Correction models from the TSD 2025 paper Refining Czech GEC: Insights from a Multi-Experiment Approach • 5 items • Updated Nov 29, 2025
75 Languages, 1 Model: Parsing Universal Dependencies Universally Paper • 1904.02099 • Published Apr 3, 2019
RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model Paper • 2105.11314 • Published May 24, 2021
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5 Paper • 2110.15248 • Published Oct 28, 2021
Leveraging Neural Machine Translation for Word Alignment Paper • 2103.17250 • Published Mar 31, 2021 • 1
Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains Paper • 2402.18747 • Published Feb 28, 2024 • 1
Early-Exit and Instant Confidence Translation Quality Estimation Paper • 2502.14429 • Published Feb 20, 2025 • 4
beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems Paper • 2409.10309 • Published Sep 16, 2024 • 4
Probing Representations Learned by Multimodal Recurrent and Transformer Models Paper • 1908.11125 • Published Aug 29, 2019