Marcin Junczys-Dowmunt

is this you? claim profile

∙ 0 followers
Adam Mickiewicz University ∙ Microsoft

Principal Research Scientist at Microsoft

Featured Co-authors

Kyunghyun Cho
162 publications
Ming Zhou
107 publications
Tie-Yan Liu
106 publications
Tao Qin
79 publications
Rico Sennrich
46 publications
Xu Tan
42 publications
Mu Li
38 publications
Ondřej Bojar
38 publications
Orhan Firat
35 publications
Shujie Liu
28 publications
Yingce Xia
25 publications

Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation

This paper describes the Microsoft Translator submissions to the WMT19 n...
07/14/2019 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora

In this work we introduce dual conditional cross-entropy filtering for n...
09/01/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data

This paper describes the Microsoft submission to the WMT2018 news transl...
09/01/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

This paper describes the Microsoft and University of Edinburgh submissio...
09/01/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation

In order to extract the best possible performance from asynchronous stoc...
08/27/2018 ∙ by Nikolay Bogoychev, et al. ∙ 0 ∙ share

read it
Marian: Cost-effective High-Quality Neural Machine Translation in C++

This paper describes the submissions of the "Marian" team to the WNMT 20...
05/30/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation

We combine two of the most popular approaches to automated Grammatical E...
04/16/2018 ∙ by Roman Grundkiewicz, et al. ∙ 0 ∙ share

read it
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task

Previously, neural methods in grammatical error correction (GEC) did not...
04/16/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Marian: Fast Neural Machine Translation in C++

We present Marian, an efficient and self-contained Neural Machine Transl...
04/01/2018 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Achieving Human Parity on Automatic Chinese to English News Translation

Machine translation has made rapid advances in recent years. Millions of...
03/15/2018 ∙ by Hany Hassan, et al. ∙ 0 ∙ share

read it
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing

In this work, we explore multiple neural architectures adapted for the t...
06/13/2017 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Nematus: a Toolkit for Neural Machine Translation

We present Nematus, a toolkit for Neural Machine Translation. The toolki...
03/13/2017 ∙ by Rico Sennrich, et al. ∙ 0 ∙ share

read it
Predicting Target Language CCG Supertags Improves Neural Machine Translation

Neural machine translation (NMT) models are able to partially learn synt...
02/03/2017 ∙ by Maria Nădejde, et al. ∙ 0 ∙ share

read it
Fast, Scalable Phrase-Based SMT Decoding

The utilization of statistical machine translation (SMT) has grown enorm...
10/13/2016 ∙ by Hieu Hoang, et al. ∙ 0 ∙ share

read it
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

In this paper we provide the largest published comparison of translation...
10/04/2016 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Target-Side Context for Discriminative Models in Statistical Machine Translation

Discriminative translation models utilizing source context have been sho...
07/05/2016 ∙ by Aleš Tamchyna, et al. ∙ 0 ∙ share

read it
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction

In this work, we study parameter tuning towards the M^2 metric, the stan...
05/20/2016 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared ta...
05/16/2016 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

This paper describes the submission of the AMU (Adam Mickiewicz Universi...
05/16/2016 ∙ by Marcin Junczys-Dowmunt, et al. ∙ 0 ∙ share

read it