76 citations · 82 across the 3 of their papers we have counts for
10 papers
Improving Fluency of Non-Autoregressive Machine Translation
Zdeněk Kasner, Jindřich Libovický, Jindřich Helcl
Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of the…
Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems
Jindřich Libovický, Alexander Fraser
Applying the Transformer architecture on the character level usually requires very deep architectures that are difficult and slow to train. These problems can be partially overcome…
On the Language Neutrality of Pre-trained Multilingual Representations
Jindřich Libovický, Rudolf Rosa, Alexander Fraser
Multilingual contextual embeddings, such as multilingual BERT and XLM-RoBERTa, have proved useful for many multi-lingual tasks. Previous work probed the cross-linguality of the rep…
How Language-Neutral is Multilingual BERT?
Jindřich Libovický, Rudolf Rosa, Alexander Fraser
Multilingual BERT (mBERT) provides sentence representations for 104 languages, which are useful for many multi-lingual tasks. Previous work probed the cross-linguality of mBERT usi…
Probing Representations Learned by Multimodal Recurrent and Transformer Models
Jindřich Libovický, Pranava Madhyastha
Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there…
Neural Networks as Explicit Word-Based Rules
Jindřich Libovický
Filters of convolutional networks used in computer vision are often visualized as image patches that maximize the response of the filter. We use the same approach to interpret weig…