Judit Acs

wordcount. Counting words in different programming languages.

wikt2dict. Wiktionary parser tool for many language editions.

snippets. Python snippets

hunaccent. Accentize Hungarian text

semeval. MathLing Budapest Team's repo

subword-choice. Code and result tables for the "Subword Pooling Makes a Difference" paper

morph-segmentation. Experimenting with supervised morphological segmentation

probing. Probing framework.

bpe. Byte pair encoding

hubert_eval. Evaluating Contextualized Language Models for Hungarian

uralic_eval. Code and data for "Evaluating Transferability of BERT Models on Uralic Languages"

koronavirus. Koronavírus statisztikák

corvinus_nlp_intro. NLP and AI introductory lecture for the Business Leadership in the Age of Artificial Intelligence class at Corvinus University

deep-morphology. PyTorch deep learning models for experiments in morphology

wiki2corpus. Fast collection of multilingual Wikipedia corpus

hunaccent-exp. Hungarian diacritic restoration

presentations. Saját prezentációk

villprog. Villamosmérnök programozás alapjai 2. órai kódrészletek

dsl. Discriminating between Similar Languages

langid. A demo version of a language identifier using trigram statistics.