paper-with-me

홈 › Papers

CUNI System for the WMT17 Multimodal Translation Task

2017-09-01 · WS 2017 9 · Jind{\v{r}}ich Helcl, Jind{\v{r}}ich Libovick{\'y}
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningMachine TranslationTranslation

Similar Papers 제목 키워드 기반

CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks

2016-06-23 · WS 2016 8 · Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Pavel Pecina 외

Neural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems. In this system description paper, we attempt to …

Automatic Post-EditingMachine TranslationMultimodal Machine TranslationTranslation

CUNI System for the WMT17 Multimodal Translation Task

2017-07-14 · 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 translation of the source image caption to the …

Image CaptioningTask 2Translation

CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT

2021-11-01 · WMT (EMNLP) 2021 11 · Petr Gebauer, Ondřej Bojar, Vojtěch Švandelík, Martin Popel

We describe our two NMT systems submitted to the WMT2021 shared task in English-Czech news translation: CUNI-DocTransformer (document-level CUBBITT) and CUNI-Marian-Baselines. We improve the former with a better sentence…

NMTSegmentationSentenceSentence segmentation+1

CUNI System for the WMT19 Robustness Task

2019-06-21 · WS 2019 8 · 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 Translation. Quantitative results show that the CU…

Translation

CUNI System for the WMT18 Multimodal Translation Task

2018-11-12 · 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. We evaluate two methods of incorporating …

Translation