4 citations · 8 across the 7 of their papers we have counts for
13 papers
SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
Raúl Vázquez, Timothee Mickus, Elaine Zosa +15
We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs).…
Lexically Grounded Subword Segmentation
Jindřich Libovický, Jindřich Helcl
We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we p…
CUNI Systems for the WMT22 Czech-Ukrainian Translation Task
Martin Popel, Jindřich Libovický, Jindřich Helcl
We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation. We present two constrained submis…
Non-Autoregressive Machine Translation: It's Not as Fast as it Seems
Jindřich Helcl, Barry Haddow, Alexandra Birch
Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest…
Survey of Low-Resource Machine Translation
Barry Haddow, Rachel Bawden, Antonio Valerio Miceli Barone +2
We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 languages spoken in the world and almost all languag…
CUNI System for the WMT19 Robustness Task
Jindřich Helcl, Jindřich Libovický, Martin Popel
We present our submission to the WMT19 Robustness Task. Our baseline system is the Charles University (CUNI) Transformer system trained for the WMT18 shared task on News Translatio…
End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification
Jindřich Libovický, Jindřich Helcl
Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the deco…
Input Combination Strategies for Multi-Source Transformer Decoder
Jindřich Libovický, Jindřich Helcl, David Mareček
In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper…
CUNI System for the WMT18 Multimodal Translation Task
Jindřich Helcl, Jindřich Libovický, Dušan Variš
We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. W…
Deep Architectures for Neural Machine Translation
Antonio Valerio Miceli Barone, Jindřich Helcl, Rico Sennrich +2
It has been shown that increasing model depth improves the quality of neural machine translation. However, different architectural variants to increase model depth have been propos…
CUNI System for the WMT17 Multimodal Translation Task
Jindřich Helcl, Jindřich Libovický
In this paper, we describe our submissions to the WMT17 Multimodal Translation Task. For Task 1 (multimodal translation), our best scoring system is a purely textual neural transla…
Attention Strategies for Multi-Source Sequence-to-Sequence Learning
Jindřich Libovický, Jindřich Helcl
Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source langu…
CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks
Jindřich Libovický, Jindřich Helcl, Marek Tlustý +2
Neural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems. In this…