no code implementations • WMT (EMNLP) 2020 • Ulrich Germann, Roman Grundkiewicz, Martin Popel, Radina Dobreva, Nikolay Bogoychev, Kenneth Heafield
We describe the joint submission of the University of Edinburgh and Charles University, Prague, to the Czech/English track in the WMT 2020 Shared Task on News Translation.
1 code implementation • WMT (EMNLP) 2021 • Maximiliana Behnke, Nikolay Bogoychev, Alham Fikri Aji, Kenneth Heafield, Graeme Nail, Qianqian Zhu, Svetlana Tchistiakova, Jelmer Van der Linde, Pinzhen Chen, Sidharth Kashyap, Roman Grundkiewicz
We participated in all tracks of the WMT 2021 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions.
1 code implementation • WMT (EMNLP) 2021 • Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell, Nikolay Bogoychev, Antonio Valerio Miceli Barone, Jonas Waldendorf, Alexandra Birch, Kenneth Heafield
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.
2 code implementations • 24 Nov 2023 • Nikolay Bogoychev, Jelmer Van der Linde, Graeme Nail, Barry Haddow, Jaume Zaragoza-Bernabeu, Gema Ramírez-Sánchez, Lukas Weymann, Tudor Nicolae Mateiu, Jindřich Helcl, Mikko Aulamo
Developing high quality machine translation systems is a labour intensive, challenging and confusing process for newcomers to the field.
no code implementations • 16 Nov 2023 • Nikolay Bogoychev, Pinzhen Chen, Barry Haddow, Alexandra Birch
Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements.
no code implementations • 9 Oct 2023 • Nikolay Bogoychev, Pinzhen Chen
Terminology correctness is important in the downstream application of machine translation, and a prevalent way to ensure this is to inject terminology constraints into a translation system.
1 code implementation • 16 Sep 2023 • Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev, Andrey Kutuzov, Barry Haddow, Kenneth Heafield
Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants.
1 code implementation • 23 May 2023 • Laurie Burchell, Alexandra Birch, Nikolay Bogoychev, Kenneth Heafield
We achieve this by training on a curated dataset of monolingual data, the reliability of which we ensure by auditing a sample from each source and each language manually.
no code implementations • 31 Mar 2023 • Ramon Sanabria, Nikolay Bogoychev, Nina Markl, Andrea Carmantini, Ondrej Klejch, Peter Bell
Although the great many advances in English automatic speech recognition (ASR) over the past decades, results are usually reported based on test datasets which fail to represent the diversity of English as spoken today around the globe.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • ACL 2022 • Andreas Grivas, Nikolay Bogoychev, Adam Lopez
Classifiers in natural language processing (NLP) often have a large number of output classes.
no code implementations • EMNLP (ACL) 2021 • Nikolay Bogoychev, Jelmer Van der Linde, Kenneth Heafield
Every day, millions of people sacrifice their privacy and browsing habits in exchange for online machine translation.
1 code implementation • EMNLP (insights) 2021 • Nikolay Bogoychev, Pinzhen Chen
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario.
1 code implementation • EMNLP (BlackboxNLP) 2021 • Nikolay Bogoychev
We show that the decision about whether a component is frozen or allowed to train is at least as important for the final model performance as its number of parameters.
1 code implementation • WS 2020 • Pin-zhen Chen, Nikolay Bogoychev, Ulrich Germann
This paper describes the University of Edinburgh{'}s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese$\leftrightarrow$Chinese translation task.
no code implementations • WS 2020 • Nikolay Bogoychev, Roman Grundkiewicz, Alham Fikri Aji, Maximiliana Behnke, Kenneth Heafield, Sidharth Kashyap, Emmanouil-Ioannis Farsarakis, Mateusz Chudyk
We participated in all tracks of the Workshop on Neural Generation and Translation 2020 Efficiency Shared Task: single-core CPU, multi-core CPU, and GPU.
1 code implementation • ACL 2020 • Pin-zhen Chen, Nikolay Bogoychev, Kenneth Heafield, Faheem Kirefu
We present a novel method to extract parallel sentences from two monolingual corpora, using neural machine translation.
no code implementations • ACL 2020 • Alham Fikri Aji, Nikolay Bogoychev, Kenneth Heafield, Rico Sennrich
Transfer learning improves quality for low-resource machine translation, but it is unclear what exactly it transfers.
no code implementations • 6 Nov 2019 • Nikolay Bogoychev, Rico Sennrich
The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data.
no code implementations • WS 2019 • Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
Taking our dominating submissions to the previous edition of the shared task as a starting point, we develop improved teacher-student training via multi-agent dual-learning and noisy backward-forward translation for Transformer-based student models.
no code implementations • IJCNLP 2019 • Alham Fikri Aji, Kenneth Heafield, Nikolay Bogoychev
One way to reduce network traffic in multi-node data-parallel stochastic gradient descent is to only exchange the largest gradients.
no code implementations • WS 2019 • Rachel Bawden, Nikolay Bogoychev, Ulrich Germann, Roman Grundkiewicz, Faheem Kirefu, Antonio Valerio Miceli Barone, Alexandra Birch
For all translation directions, we created or used back-translations of monolingual data in the target language as additional synthetic training data.
no code implementations • WS 2019 • Lushi Chen, Abeer Aldayel, Nikolay Bogoychev, Tao Gong
We approached the problem with three separate models: a behaviour model; a language model and a hybrid model.
no code implementations • WS 2018 • Barry Haddow, Nikolay Bogoychev, Denis Emelin, Ulrich Germann, Roman Grundkiewicz, Kenneth Heafield, Antonio Valerio Miceli Barone, Rico Sennrich
The University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs.
no code implementations • EMNLP 2018 • Nikolay Bogoychev, Marcin Junczys-Dowmunt, Kenneth Heafield, Alham Fikri Aji
In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly.
2 code implementations • ACL 2018 • Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, Alexandra Birch
We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.
no code implementations • AMTA 2016 • Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community.