paper-with-me

Papers

The University of Edinburgh's Neural MT Systems for WMT17

2017-08-02 · WS 2017 9 · Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams

This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russian, Turkish and Chinese. For the biomedical task we submitted systems for English to Czech, German, Polish and Romanian. Our systems are neural machine translation systems trained with Nematus, an attentional encoder-decoder. We follow our setup from last year and build BPE-based models with parallel and back-translated monolingual training data. Novelties this year include the use of deep architectures, layer normalization, and more compact models due to weight tying and improvements in BPE segmentations. We perform extensive ablative experiments, reporting on the effectivenes of layer normalization, deep architectures, and different ensembling techniques.

📄 PDF Abstract BibTeX arXiv:1708.00726

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

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…
Weight Tying Weight Tying improves the performance of language models by tying (sharing) the weights of the embedding and softmax layers. This…

Similar Papers 제목 키워드 기반

Samsung and University of Edinburgh’s System for the IWSLT 2019

2019-11-01 · EMNLP (IWSLT) 2019 11 · Joanna Wetesko, Marcin Chochowski, Pawel Przybysz, Philip Williams 외

This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung RD Institute, Poland, and the University of Edinburgh. Our submission was ultimately produced by combining four Transformer sys…

Reranking

The University of Edinburgh’s submission to the German-to-English and English-to-German Tracks in the WMT 2020 News Translation and Zero-shot Translation Robustness Tasks

2020-11-01 · WMT (EMNLP) 2020 11 · Ulrich Germann

This paper describes the University of Edinburgh’s submission of German <-> English systems to the WMT2020 Shared Tasks on News Translation and Zero-shot Robustness.

Translation

The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task

2021-11-01 · WMT (EMNLP) 2021 11 · Proyag Pal, Alham Fikri Aji, Pinzhen Chen, Sukanta Sen

We describe the University of Edinburgh’s Bengali\leftrightarrowHindi constrained systems submitted to the WMT21 News Translation task. We submitted ensembles of Transformer models built with large-scale back-translation…

Translation

The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task

2021-11-01 · WMT (EMNLP) 2021 11 · Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell 외

This paper presents the University of Edinburgh’s constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation. We build En-De systems in three stages: corpus filter…

Translation

The University of Edinburgh’s systems submission to the MT task at IWSLT

2016-12-01 · IWSLT 2016 12 · Marcin Junczys-Dowmunt, Alexandra Birch

This paper describes the submission of the University of Edinburgh team to the IWSLT MT task for TED talks. We took part in four translation directions, en-de, de-en, en-fr, and fr-en. The models have been trained with a…

Decoderde-enDomain Adaptationfr-en+1