38 citations · 117 across the 22 of their papers we have counts for
5 papers · 1 filter
Character Transformations for Non-Autoregressive GEC Tagging
Milan Straka, Jakub Náplava, Jana Straková
We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has prove…
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5
David Samuel, Milan Straka
We present the winning entry to the Multilingual Lexical Normalization (MultiLexNorm) shared task at W-NUT 2021 (van der Goot et al., 2021a), which evaluates lexical-normalization…
Understanding Model Robustness to User-generated Noisy Texts
Jakub Náplava, Martin Popel, Milan Straka +1
Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling…
Diacritics Restoration using BERT with Analysis on Czech language
Jakub Náplava, Milan Straka, Jana Straková
We propose a new architecture for diacritics restoration based on contextualized embeddings, namely BERT, and we evaluate it on 12 languages with diacritics. Furthermore, we conduc…
RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model
Milan Straka, Jakub Náplava, Jana Straková +1
We present RobeCzech, a monolingual RoBERTa language representation model trained on Czech data. RoBERTa is a robustly optimized Transformer-based pretraining approach. We show tha…