paper-with-me

홈 › Papers

CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

2022-12-01 · Jindřich Helcl

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.

📄 PDF Abstract BibTeX arXiv:2212.00477

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

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 Systems for the Unsupervised News Translation Task in WMT 2019

2019-07-29 · Ivana Kvapilíková, Dominik Macháček, Ondřej Bojar

In this paper we describe the CUNI translation system used for the unsupervised news shared task of the ACL 2019 Fourth Conference on Machine Translation (WMT19). We follow the strategy of Artexte et al. (2018b), creatin…

Machine TranslationTranslation

CUNI Systems for the Unsupervised News Translation Task in WMT 2019

2019-08-01 · WS 2019 8 · Ivana Kvapil{\'\i}kov{\'a}, Dominik Mach{\'a}{\v{c}}ek, Ond{\v{r}}ej Bojar

In this paper we describe the CUNI translation system used for the unsupervised news shared task of the ACL 2019 Fourth Conference on Machine Translation (WMT19). We follow the strategy of Artetxe ae at. (2018b), creatin…

Machine TranslationTranslation

CUNI Submission for the Inuktitut Language in WMT News 2020

2020-11-01 · WMT (EMNLP) 2020 11 · Tom Kocmi

This paper describes CUNI submission to the WMT 2020 News Translation Shared Task for the low-resource scenario Inuktitut–English in both translation directions. Our system combines transfer learning from a Czech–English…

Transfer LearningTranslation