Marcin Junczys-Dowmunt

85 papers A* 3A 1B 1C 4Journal 31Unranked 43
YearRankTypeTitle / Venue / Authors
2024 — conf
Evaluation and Large-scale Training for Contextual Machine Translation.
WMT
Matt Post, Marcin Junczys-Dowmunt
2024 — conf
On Instruction-Finetuning Neural Machine Translation Models.
WMT
Vikas Raunak, Roman Grundkiewicz, Marcin Junczys-Dowmunt
2024 J jnl
On Instruction-Finetuning Neural Machine Translation Models.
CoRR
Vikas Raunak, Roman Grundkiewicz, Marcin Junczys-Dowmunt
2024 — conf
On-the-Fly Fusion of Large Language Models and Machine Translation.
NAACL-HLT (Findings)
Hieu Hoang, Huda Khayrallah, Marcin Junczys-Dowmunt
2024 — conf
PyMarian: Fast Neural Machine Translation and Evaluation in Python.
EMNLP (System Demonstrations)
Thamme Gowda, Roman Grundkiewicz, Elijah Rippeth, Matt Post, Marcin Junczys-Dowmunt
2024 J jnl
PyMarian: Fast Neural Machine Translation and Evaluation in Python.
CoRR
Thamme Gowda, Roman Grundkiewicz, Elijah Rippeth, Matt Post, Marcin Junczys-Dowmunt
2023 — conf
Cometoid: Distilling Strong Reference-based Machine Translation Metrics into Even Stronger Quality Estimation Metrics.
WMT
Thamme Gowda, Tom Kocmi, Marcin Junczys-Dowmunt
2023 J jnl
Escaping the sentence-level paradigm in machine translation.
CoRR
Matt Post, Marcin Junczys-Dowmunt
2023 J jnl
On-the-Fly Fusion of Large Language Models and Machine Translation.
CoRR
Hieu Hoang, Huda Khayrallah, Marcin Junczys-Dowmunt
2023 — conf
Perplexity-Driven Case Encoding Needs Augmentation for CAPITALIZATION Robustness.
IJCNLP (2)
Rohit Jain, Huda Khayrallah, Roman Grundkiewicz, Marcin Junczys-Dowmunt
2023 J jnl
SOTASTREAM: A Streaming Approach to Machine Translation Training.
CoRR
Matt Post, Thamme Gowda, Roman Grundkiewicz, Huda Khayrallah, Rohit Jain, Marcin Junczys-Dowmunt
2022 — conf
Revisiting Locality Sensitive Hashing for Vocabulary Selection in Fast Neural Machine Translation.
WMT
Hieu Hoang, Marcin Junczys-Dowmunt, Roman Grundkiewicz, Huda Khayrallah
2021 — conf
Levenshtein Training for Word-level Quality Estimation.
EMNLP (1)
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn
2021 J jnl
Levenshtein Training for Word-level Quality Estimation.
CoRR
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn
2021 J jnl
On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs.
CoRR
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Christian Federmann, Tom Kocmi
2021 — conf
The Curious Case of Hallucinations in Neural Machine Translation.
NAACL-HLT
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
2021 J jnl
The Curious Case of Hallucinations in Neural Machine Translation.
CoRR
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
2021 — conf
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task.
WMT@EMNLP
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Christian Federmann, Philipp Koehn
2021 J jnl
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task.
CoRR
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Christian Federmann, Philipp Koehn
2021 — conf
To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation.
WMT@EMNLP
Tom Kocmi, Christian Federmann, Roman Grundkiewicz, Marcin Junczys-Dowmunt, Hitokazu Matsushita, Arul Menezes
2021 J jnl
To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation.
CoRR
Tom Kocmi, Christian Federmann, Roman Grundkiewicz, Marcin Junczys-Dowmunt, Hitokazu Matsushita, Arul Menezes
2020 — ed.
Proceedings of the Fourth Workshop on Neural Generation and Translation, NGT@ACL 2020, Online, July 5-10, 2020
NGT@ACL
Alexandra Birch, Andrew M. Finch, Hiroaki Hayashi, Kenneth Heafield, Marcin Junczys-Dowmunt, Ioannis Konstas, Xian Li, Graham Neubig, Yusuke Oda
2019 — conf
From Research to Production and Back: Ludicrously Fast Neural Machine Translation.
NGT@EMNLP-IJCNLP
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
2019 — conf
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation.
WMT (2)
Marcin Junczys-Dowmunt
2019 J jnl
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation.
CoRR
Marcin Junczys-Dowmunt
2019 — conf
Minimally-Augmented Grammatical Error Correction.
W-NUT@EMNLP
Roman Grundkiewicz, Marcin Junczys-Dowmunt
2019 — conf
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data.
BEA@ACL
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Kenneth Heafield
2018 A* conf
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation.
EMNLP
Nikolay Bogoychev, Kenneth Heafield, Alham Fikri Aji, Marcin Junczys-Dowmunt
2018 J jnl
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation.
CoRR
Nikolay Bogoychev, Marcin Junczys-Dowmunt, Kenneth Heafield, Alham Fikri Aji
2018 J jnl
Achieving Human Parity on Automatic Chinese to English News Translation.
CoRR
Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, Shujie Liu, Tie-Yan Liu, Renqian Luo, Arul Menezes, Tao Qin, Frank Seide, Xu Tan, Fei Tian, Lijun Wu, Shuangzhi Wu, Yingce Xia, Dongdong Zhang, Zhirui Zhang, Ming Zhou
2018 — conf
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task.
NAACL-HLT
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield
2018 J jnl
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task.
CoRR
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield
2018 — conf
Are we experiencing the Golden Age of Automatic Post-Editing?
PostEditing@AMTA
Marcin Junczys-Dowmunt
2018 — conf
Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora.
WMT (shared task)
Marcin Junczys-Dowmunt
2018 J jnl
Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora.
CoRR
Marcin Junczys-Dowmunt
2018 — conf
MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing.
WMT (shared task)
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2018 J jnl
MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing.
CoRR
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2018 — conf
Marian: Cost-effective High-Quality Neural Machine Translation in C++.
NMT@ACL
Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue
2018 J jnl
Marian: Cost-effective High-Quality Neural Machine Translation in C++.
CoRR
Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue
2018 — conf
Marian: Fast Neural Machine Translation in C++.
ACL (4)
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
2018 J jnl
Marian: Fast Neural Machine Translation in C++.
CoRR
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
2018 — conf
Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data.
WMT (shared task)
Marcin Junczys-Dowmunt
2018 J jnl
Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data.
CoRR
Marcin Junczys-Dowmunt
2018 — conf
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation.
NAACL-HLT (2)
Roman Grundkiewicz, Marcin Junczys-Dowmunt
2018 J jnl
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation.
CoRR
Roman Grundkiewicz, Marcin Junczys-Dowmunt
2017 — conf
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing.
IJCNLP(1)
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2017 J jnl
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing.
CoRR
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2017 — conf
Nematus: a Toolkit for Neural Machine Translation.
EACL (Software Demonstrations)
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nadejde
2017 J jnl
Nematus: a Toolkit for Neural Machine Translation.
CoRR
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nadejde
2017 — conf
Predicting Target Language CCG Supertags Improves Neural Machine Translation.
WMT
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch
2017 J jnl
Pushing the Limits of Translation Quality Estimation.
Trans. Assoc. Comput. Linguistics
André F. T. Martins, Marcin Junczys-Dowmunt, Fábio N. Kepler, Ramón Fernandez Astudillo, Chris Hokamp, Roman Grundkiewicz
2017 J jnl
Syntax-aware Neural Machine Translation Using CCG.
CoRR
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch
2017 — conf
The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing.
WMT
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2017 — conf
The SUMMA Platform Prototype.
EACL (Software Demonstrations)
Renars Liepins, Ulrich Germann, Guntis Barzdins, Alexandra Birch, Steve Renals, Susanne Weber, Peggy van der Kreeft, Hervé Bourlard, João Prieto, Ondrej Klejch, Peter Bell, Alexandros Lazaridis, Afonso Mendes, Sebastian Riedel, Mariana S. C. Almeida, Pedro Balage, Shay B. Cohen, Tomasz Dwojak, Philip N. Garner, Andreas Giefer, Marcin Junczys-Dowmunt, Hina Imran, David Nogueira, Ahmed M. Ali, Sebastião Miranda, Andrei Popescu-Belis, Lesly Miculicich Werlen, Nikos Papasarantopoulos, Abiola Obamuyide, Clive Jones, Fahim Dalvi, Andreas Vlachos, Yang Wang, Sibo Tong, Rico Sennrich, Nikolaos Pappas, Shashi Narayan, Marco Damonte, Nadir Durrani, Sameer Khurana, Ahmed Abdelali, Hassan Sajjad, Stephan Vogel, David Sheppey, Chris Hernon, Jeff Mitchell
2016 — conf
Fast, Scalable Phrase-Based SMT Decoding.
AMTA (1)
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
2016 J jnl
Fast, Scalable Phrase-Based SMT Decoding.
CoRR
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
2016 — conf
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions.
IWSLT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang
2016 J jnl
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions.
CoRR
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang
2016 — conf
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing.
WMT
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2016 J jnl
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing.
CoRR
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2016 A* conf
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction.
EMNLP
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2016 J jnl
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction.
CoRR
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2016 — conf
Target-Side Context for Discriminative Models in Statistical Machine Translation.
ACL (1)
Ales Tamchyna, Alexander M. Fraser, Ondrej Bojar, Marcin Junczys-Dowmunt
2016 J jnl
Target-Side Context for Discriminative Models in Statistical Machine Translation.
CoRR
Ales Tamchyna, Alexander M. Fraser, Ondrej Bojar, Marcin Junczys-Dowmunt
2016 — conf
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT.
WMT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
2016 J jnl
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT.
CoRR
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
2016 B conf
The United Nations Parallel Corpus v1.0.
LREC
Michal Ziemski, Marcin Junczys-Dowmunt, Bruno Pouliquen
2016 — conf
The University of Edinburgh's systems submission to the MT task at IWSLT.
IWSLT
Marcin Junczys-Dowmunt, Alexandra Birch
2015 A* conf
Human Evaluation of Grammatical Error Correction Systems.
EMNLP
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Edward Gillian
2015 A conf
Large scale speech-to-text translation with out-of-domain corpora using better context-based models and domain adaptation.
INTERSPEECH
Marcin Junczys-Dowmunt, Pawel Przybysz, Arleta Staszuk, Eun-Kyoung Kim, Jaewon Lee
2015 — conf
Reinvestigating the Classification Approach to the Article and Preposition Error Correction.
LTC
Roman Grundkiewicz, Marcin Junczys-Dowmunt
2015 C conf
SMT at the International Maritime Organization: experiences with combining in-house corpora with out-of-domain corpora.
EAMT
Bruno Pouliquen, Marcin Junczys-Dowmunt, Blanca Pinero, Michal Ziemski
2014 C conf
SMT of German patents at WIPO: decompounding and verb structure pre-reordering.
EAMT
Marcin Junczys-Dowmunt, Bruno Pouliquen
2014 — conf
The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine Translation.
CoNLL Shared Task
Marcin Junczys-Dowmunt, Roman Grundkiewicz
2014 — conf
The WikEd Error Corpus: A Corpus of Corrective Wikipedia Edits and Its Application to Grammatical Error Correction.
PolTAL
Roman Grundkiewicz, Marcin Junczys-Dowmunt
2013 — ch.
PSI-Toolkit: A Natural Language Processing Pipeline.
Computational Linguistics - Applications
Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt
2012 — conf
A Genetic Programming Experiment in Natural Language Grammar Engineering.
TSD
Marcin Junczys-Dowmunt
2012 C conf
A Phrase Table without Phrases: Rank Encoding for Better Phrase Table Compression.
EAMT
Marcin Junczys-Dowmunt
2012 — conf
A Space-Efficient Phrase Table Implementation Using Minimal Perfect Hash Functions.
TSD
Marcin Junczys-Dowmunt
2012 J jnl
Phrasal Rank-Encoding: Exploiting Phrase Redundancy and Translational Relations for Phrase Table Compression.
Prague Bull. Math. Linguistics
Marcin Junczys-Dowmunt
2011 — conf
SyMGiza++: Symmetrized Word Alignment Models for Statistical Machine Translation.
SIIS
Marcin Junczys-Dowmunt, Arkadiusz Szal
2010 C conf
A Maximum Entropy Approach to Syntactic Translation Rule Filtering.
CICLing
Marcin Junczys-Dowmunt
2010 — conf
SyMGiza++: A Tool for Parallel Computation of Symmetrized Word Alignment Models.
IMCSIT
Marcin Junczys-Dowmunt, Arkadiusz Szal
2009 — conf
It's all about the trees towards a hybrid syntax-based MT system.
IMCSIT
Marcin Junczys-Dowmunt
2008 — conf
Influence of accurate compound noun splitting on bilingual vocabulary extraction.
KONVENS
Marcin Junczys-Dowmunt