8 citations · 11 across the 5 of their papers we have counts for
6 papers
Syntax-based data augmentation for Hungarian-English machine translation
Attila Nagy, Patrick Nanys, Balázs Frey Konrád +2
We train Transformer-based neural machine translation models for Hungarian-English and English-Hungarian using the Hunglish2 corpus. Our best models achieve a BLEU score of 40.0 on…
A Three Step Training Approach with Data Augmentation for Morphological Inflection
Gabor Szolnok, Botond Barta, Dorina Lakatos +1
We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with th…
Subword Pooling Makes a Difference
Judit Ács, Ákos Kádár, András Kornai
Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown word…
Evaluating Contextualized Language Models for Hungarian
Judit Ács, Dániel Lévai, Dávid Márk Nemeskey +1
We present an extended comparison of contextualized language models for Hungarian. We compare huBERT, a Hungarian model against 4 multilingual models including the multilingual BER…
Automatic punctuation restoration with BERT models
Attila Nagy, Bence Bial, Judit Ács
We present an approach for automatic punctuation restoration with BERT models for English and Hungarian. For English, we conduct our experiments on Ted Talks, a commonly used bench…
The Role of Interpretable Patterns in Deep Learning for Morphology
Judit Acs, Andras Kornai
We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, wher…