activity
20162020
most citedHow Language-Neutral is Multilingual BERT?

76 citations · 82 across the 3 of their papers we have counts for

collaborators

10 papers

cs.CL20206 cited

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…

cs.CL2020

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…

cs.CL2020

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…

cs.CL201976 cited

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…

cs.CL2019

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…

cs.CL2019

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…