Levenshtein Training for Word-level Quality Estimation
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn
2021 Empirical Methods in Natural Language Processing | September 2021
Marcin Junczys-Dowmunt
Principal NLP Scientist
Publications
Publications by Year
-
The Curious Case of Hallucinations in Neural Machine Translation
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
NAACL 2021 | April 2021
-
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
-
Achieving Human Parity on Automatic Chinese to English News Translation
Hany Hassan Awadalla, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, Will 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
March 2018
arXiv:1803.05567
-
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
IJCNLP 2017 | June 2017
Pushing the limits of translation quality estimation
André F.T. Martins, Marcin Junczys-Dowmunt, Fabio N. Kepler, Ramón Astudillo, Chris Hokamp, Roman Grundkiewicz
Transactions of the Association for Computational Linguistics | May 2017, Vol 5: pp. 205-218
The SUMMA Platform Prototype
Marcin Junczys-Dowmunt, et al
Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics | May 2017
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch
Proceedings of the Second Conference on Machine Translation | April 2017
The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Second Conference on Machine Translation | April 2017
Nematus: a Toolkit for Neural Machine Translation
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Laubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nadejde
March 2017
arXiv:1703.04357
Reinvestigating the Classification Approach to the Article and Preposition Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
LTC 2015: Human Language Technology. Challenges for Computer Science and Linguistics | February 2017
-
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing | November 2016
Fast, scalable phrase-based smt decoding
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
October 2016
arXiv:1610.04265
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang
IWSLT 2016, Seattle | October 2016
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
Proceedings of the First Conference on Machine Translation (WMT 16) | August 2016
COPPA V2. 0: Corpus Of Parallel Patent Applications Building Large Parallel Corpora with GNU Make
Marcin Junczys-Dowmunt, Bruno Pouliquen, Christophe Mazenc
4th Workshop on Challenges in the Management of Large Corpora Workshop Programme | May 2016
The United Nations Parallel Corpus v1. 0
Michal Ziemski, Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016 | April 2016
The University of Edinburgh’s systems submission to the MT task at IWSLT
Marcin Junczys-Dowmunt, Alexandra Birch
Proceedings of the First Conference on Machine Translation, Seattle, USA | April 2016
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the First Conference on Machine Translation (WMT 16) | April 2016
Target-Side Context for Discriminative Models in Statistical Machine Translation
Ales Tamchyna, Alexander Fraser, Ondrej Bojar, Marcin Junczys-Dowmunt
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 | April 2016
-
Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation
Marcin Junczys-Dowmunt, Paweł Przybysz, Arleta Staszuk, Eun-Kyoung Kim, Jaewon Lee
INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association | September 2015
Human evaluation of grammatical error correction systems
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Edward Gillian
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing | April 2015
SMT at the International Maritime Organization: Experiences with Combining In-house Corpora with Out-of-domain Corpora
Bruno Pouliquen, Marcin Junczys-Dowmunt, Blanca Pinero, Michal Ziemski
European Association for Machine Translation 2015 | April 2015
-
The WikEd Error Corpus: A Corpus of Corrective Wikipedia Edits and its Application to Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
International Conference on Natural Language Processing | September 2014
SMT of German Patents at WIPO: Decompounding and Verb Structure Pre-reordering
Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the 17th Annual Conference of the European Association for Machine Translation (EAMT2014) | June 2014
The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine Translation
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task | May 2014
-
Large-scale multiple language translation accelerator at the United Nations
Bruno Pouliquen, Cecilia Elizalde, Marcin Junczys-Dowmunt, Christophe Mazenc, José García-Verdugo
Proceedings of the 14th Machine Translation Summit | April 2013
-
Phrasal rank-encoding: Exploiting phrase redundancy and translational relations for phrase table compression
The Prague Bulletin of Mathematical Linguistics | October 2012, Vol 98: pp. 63-74
Phrasal Rank-Encoding
September 2012
A Genetic Programming Experiment in Natural Language Grammar Engineering
International Conference on Text, Speech and Dialogue | September 2012
A space-efficient phrase table implementation using minimal perfect hash functions
International Conference on Text, Speech and Dialogue | September 2012
A phrase table without phrases: Rank encoding for better phrase table Compression
Proceedings of the 16th Annual Conference of the European Association for Machine Translation | April 2012
PSI-toolkit: A Natural Language Processing Pipeline
Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt
Computational Linguistics | April 2012, Vol 458: pp. 27-39
Computational Linguistics
Editor(s): Adam PrzepiórkowskiMaciej PiaseckiKrzysztof JassemPiotr Fuglewicz
SyMGiza++: Symmetrized word alignment models for statistical machine translation
Marcin Junczys-Dowmunt, Arkadiusz Szal
International Joint Conference of Security and Intelligent Information Systems | April 2012
-
SyMGiza++: A tool for parallel computation of symmetrized word alignment models
Marcin Junczys-Dowmunt, Arkadiusz Szał
Proceedings of the 2010 International Multiconference on Computer Science and Information Technology (IMCSIT) | October 2010
ISBN: 978-1-4244-6432-6
A Maximum Entropy Approach to Syntactic Translation Rule Filtering
CICLing 2010: Computational Linguistics and Intelligent Text Processing | April 2010
-
It’s all about the trees towards a hybrid syntax-based MT system
International Multiconference on Computer Science and Information Technology, 2009. IMCSIT'09 | October 2009
ISBN: 978-1-4244-5314-6
PSI-Toolkit–an Extensible and Tightly Integrated Set of NLP Tools
Marcin Junczys-Dowmunt, et al
April 2009
-
Wprowadzenie do metod statystycznych w tłumaczeniu automatycznym
Investigationes Linguisticae | December 2008, Vol 16
Influence of accurate compound noun splitting on bilingual vocabulary extraction
KONVENS | November 2008
-
Model skończenie stanowy niemieckich wyrazów pojedynczo i wielokrotnie złożonych
Investigationes Linguisticae | June 2007, pp. 50-67
Using a Treebank Grammar for the Syntactical Annotation of German Lexical Phrases
Marcin Junczys-Dowmunt, Filip Gralinski
Proceedings of 3rd L&T Conference | January 2007
-
Grammatical Error Correction with (almost) no Linguistic Knowledge
Roman Grundkiewicz, Marcin Junczys-Dowmunt
May 2004, pp. 240-243
Publications by Research Area
-
Levenshtein Training for Word-level Quality Estimation
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn
2021 Empirical Methods in Natural Language Processing | September 2021
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
-
The Curious Case of Hallucinations in Neural Machine Translation
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
NAACL 2021 | April 2021
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
Achieving Human Parity on Automatic Chinese to English News Translation
Hany Hassan Awadalla, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, Will 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
March 2018
arXiv:1803.05567
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
IJCNLP 2017 | June 2017
The SUMMA Platform Prototype
Marcin Junczys-Dowmunt, et al
Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics | May 2017
Pushing the limits of translation quality estimation
André F.T. Martins, Marcin Junczys-Dowmunt, Fabio N. Kepler, Ramón Astudillo, Chris Hokamp, Roman Grundkiewicz
Transactions of the Association for Computational Linguistics | May 2017, Vol 5: pp. 205-218
The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Second Conference on Machine Translation | April 2017
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch
Proceedings of the Second Conference on Machine Translation | April 2017
Nematus: a Toolkit for Neural Machine Translation
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Laubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nadejde
March 2017
arXiv:1703.04357
Reinvestigating the Classification Approach to the Article and Preposition Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
LTC 2015: Human Language Technology. Challenges for Computer Science and Linguistics | February 2017
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing | November 2016
Fast, scalable phrase-based smt decoding
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
October 2016
arXiv:1610.04265
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang
IWSLT 2016, Seattle | October 2016
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
Proceedings of the First Conference on Machine Translation (WMT 16) | August 2016
COPPA V2. 0: Corpus Of Parallel Patent Applications Building Large Parallel Corpora with GNU Make
Marcin Junczys-Dowmunt, Bruno Pouliquen, Christophe Mazenc
4th Workshop on Challenges in the Management of Large Corpora Workshop Programme | May 2016
The University of Edinburgh’s systems submission to the MT task at IWSLT
Marcin Junczys-Dowmunt, Alexandra Birch
Proceedings of the First Conference on Machine Translation, Seattle, USA | April 2016
The United Nations Parallel Corpus v1. 0
Michal Ziemski, Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016 | April 2016
Target-Side Context for Discriminative Models in Statistical Machine Translation
Ales Tamchyna, Alexander Fraser, Ondrej Bojar, Marcin Junczys-Dowmunt
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 | April 2016
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the First Conference on Machine Translation (WMT 16) | April 2016
Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation
Marcin Junczys-Dowmunt, Paweł Przybysz, Arleta Staszuk, Eun-Kyoung Kim, Jaewon Lee
INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association | September 2015
Human evaluation of grammatical error correction systems
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Edward Gillian
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing | April 2015
SMT at the International Maritime Organization: Experiences with Combining In-house Corpora with Out-of-domain Corpora
Bruno Pouliquen, Marcin Junczys-Dowmunt, Blanca Pinero, Michal Ziemski
European Association for Machine Translation 2015 | April 2015
The WikEd Error Corpus: A Corpus of Corrective Wikipedia Edits and its Application to Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
International Conference on Natural Language Processing | September 2014
SMT of German Patents at WIPO: Decompounding and Verb Structure Pre-reordering
Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the 17th Annual Conference of the European Association for Machine Translation (EAMT2014) | June 2014
The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine Translation
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task | May 2014
Large-scale multiple language translation accelerator at the United Nations
Bruno Pouliquen, Cecilia Elizalde, Marcin Junczys-Dowmunt, Christophe Mazenc, José García-Verdugo
Proceedings of the 14th Machine Translation Summit | April 2013
Phrasal rank-encoding: Exploiting phrase redundancy and translational relations for phrase table compression
The Prague Bulletin of Mathematical Linguistics | October 2012, Vol 98: pp. 63-74
Phrasal Rank-Encoding
September 2012
A Genetic Programming Experiment in Natural Language Grammar Engineering
International Conference on Text, Speech and Dialogue | September 2012
A space-efficient phrase table implementation using minimal perfect hash functions
International Conference on Text, Speech and Dialogue | September 2012
A phrase table without phrases: Rank encoding for better phrase table Compression
Proceedings of the 16th Annual Conference of the European Association for Machine Translation | April 2012
SyMGiza++: Symmetrized word alignment models for statistical machine translation
Marcin Junczys-Dowmunt, Arkadiusz Szal
International Joint Conference of Security and Intelligent Information Systems | April 2012
PSI-toolkit: A Natural Language Processing Pipeline
Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt
Computational Linguistics | April 2012, Vol 458: pp. 27-39
Computational Linguistics
Editor(s): Adam PrzepiórkowskiMaciej PiaseckiKrzysztof JassemPiotr Fuglewicz
SyMGiza++: A tool for parallel computation of symmetrized word alignment models
Marcin Junczys-Dowmunt, Arkadiusz Szał
Proceedings of the 2010 International Multiconference on Computer Science and Information Technology (IMCSIT) | October 2010
ISBN: 978-1-4244-6432-6
A Maximum Entropy Approach to Syntactic Translation Rule Filtering
CICLing 2010: Computational Linguistics and Intelligent Text Processing | April 2010
It’s all about the trees towards a hybrid syntax-based MT system
International Multiconference on Computer Science and Information Technology, 2009. IMCSIT'09 | October 2009
ISBN: 978-1-4244-5314-6
PSI-Toolkit–an Extensible and Tightly Integrated Set of NLP Tools
Marcin Junczys-Dowmunt, et al
April 2009
Wprowadzenie do metod statystycznych w tłumaczeniu automatycznym
Investigationes Linguisticae | December 2008, Vol 16
Influence of accurate compound noun splitting on bilingual vocabulary extraction
KONVENS | November 2008
Model skończenie stanowy niemieckich wyrazów pojedynczo i wielokrotnie złożonych
Investigationes Linguisticae | June 2007, pp. 50-67
Using a Treebank Grammar for the Syntactical Annotation of German Lexical Phrases
Marcin Junczys-Dowmunt, Filip Gralinski
Proceedings of 3rd L&T Conference | January 2007
Grammatical Error Correction with (almost) no Linguistic Knowledge
Roman Grundkiewicz, Marcin Junczys-Dowmunt
May 2004, pp. 240-243
Publications by Type
-
Levenshtein Training for Word-level Quality Estimation
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn
2021 Empirical Methods in Natural Language Processing | September 2021
The Curious Case of Hallucinations in Neural Machine Translation
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
NAACL 2021 | April 2021
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
IJCNLP 2017 | June 2017
The SUMMA Platform Prototype
Marcin Junczys-Dowmunt, et al
Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics | May 2017
The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Second Conference on Machine Translation | April 2017
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch
Proceedings of the Second Conference on Machine Translation | April 2017
Reinvestigating the Classification Approach to the Article and Preposition Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
LTC 2015: Human Language Technology. Challenges for Computer Science and Linguistics | February 2017
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing | November 2016
Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang
IWSLT 2016, Seattle | October 2016
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
Proceedings of the First Conference on Machine Translation (WMT 16) | August 2016
COPPA V2. 0: Corpus Of Parallel Patent Applications Building Large Parallel Corpora with GNU Make
Marcin Junczys-Dowmunt, Bruno Pouliquen, Christophe Mazenc
4th Workshop on Challenges in the Management of Large Corpora Workshop Programme | May 2016
The University of Edinburgh’s systems submission to the MT task at IWSLT
Marcin Junczys-Dowmunt, Alexandra Birch
Proceedings of the First Conference on Machine Translation, Seattle, USA | April 2016
The United Nations Parallel Corpus v1. 0
Michal Ziemski, Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016 | April 2016
Target-Side Context for Discriminative Models in Statistical Machine Translation
Ales Tamchyna, Alexander Fraser, Ondrej Bojar, Marcin Junczys-Dowmunt
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 | April 2016
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the First Conference on Machine Translation (WMT 16) | April 2016
Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation
Marcin Junczys-Dowmunt, Paweł Przybysz, Arleta Staszuk, Eun-Kyoung Kim, Jaewon Lee
INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association | September 2015
Human evaluation of grammatical error correction systems
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Edward Gillian
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing | April 2015
SMT at the International Maritime Organization: Experiences with Combining In-house Corpora with Out-of-domain Corpora
Bruno Pouliquen, Marcin Junczys-Dowmunt, Blanca Pinero, Michal Ziemski
European Association for Machine Translation 2015 | April 2015
The WikEd Error Corpus: A Corpus of Corrective Wikipedia Edits and its Application to Grammatical Error Correction
Roman Grundkiewicz, Marcin Junczys-Dowmunt
International Conference on Natural Language Processing | September 2014
SMT of German Patents at WIPO: Decompounding and Verb Structure Pre-reordering
Marcin Junczys-Dowmunt, Bruno Pouliquen
Proceedings of the 17th Annual Conference of the European Association for Machine Translation (EAMT2014) | June 2014
The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine Translation
Marcin Junczys-Dowmunt, Roman Grundkiewicz
Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task | May 2014
Large-scale multiple language translation accelerator at the United Nations
Bruno Pouliquen, Cecilia Elizalde, Marcin Junczys-Dowmunt, Christophe Mazenc, José García-Verdugo
Proceedings of the 14th Machine Translation Summit | April 2013
A Genetic Programming Experiment in Natural Language Grammar Engineering
International Conference on Text, Speech and Dialogue | September 2012
A space-efficient phrase table implementation using minimal perfect hash functions
International Conference on Text, Speech and Dialogue | September 2012
A phrase table without phrases: Rank encoding for better phrase table Compression
Proceedings of the 16th Annual Conference of the European Association for Machine Translation | April 2012
SyMGiza++: Symmetrized word alignment models for statistical machine translation
Marcin Junczys-Dowmunt, Arkadiusz Szal
International Joint Conference of Security and Intelligent Information Systems | April 2012
SyMGiza++: A tool for parallel computation of symmetrized word alignment models
Marcin Junczys-Dowmunt, Arkadiusz Szał
Proceedings of the 2010 International Multiconference on Computer Science and Information Technology (IMCSIT) | October 2010
ISBN: 978-1-4244-6432-6
A Maximum Entropy Approach to Syntactic Translation Rule Filtering
CICLing 2010: Computational Linguistics and Intelligent Text Processing | April 2010
It’s all about the trees towards a hybrid syntax-based MT system
International Multiconference on Computer Science and Information Technology, 2009. IMCSIT'09 | October 2009
ISBN: 978-1-4244-5314-6
Influence of accurate compound noun splitting on bilingual vocabulary extraction
KONVENS | November 2008
Using a Treebank Grammar for the Syntactical Annotation of German Lexical Phrases
Marcin Junczys-Dowmunt, Filip Gralinski
Proceedings of 3rd L&T Conference | January 2007
-
Achieving Human Parity on Automatic Chinese to English News Translation
Hany Hassan Awadalla, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, Will 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
March 2018
arXiv:1803.05567
Nematus: a Toolkit for Neural Machine Translation
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Laubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nadejde
March 2017
arXiv:1703.04357
Fast, scalable phrase-based smt decoding
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt
October 2016
arXiv:1610.04265
-
Phrasal Rank-Encoding
September 2012
PSI-Toolkit–an Extensible and Tightly Integrated Set of NLP Tools
Marcin Junczys-Dowmunt, et al
April 2009
Grammatical Error Correction with (almost) no Linguistic Knowledge
Roman Grundkiewicz, Marcin Junczys-Dowmunt
May 2004, pp. 240-243
-
Pushing the limits of translation quality estimation
André F.T. Martins, Marcin Junczys-Dowmunt, Fabio N. Kepler, Ramón Astudillo, Chris Hokamp, Roman Grundkiewicz
Transactions of the Association for Computational Linguistics | May 2017, Vol 5: pp. 205-218
Phrasal rank-encoding: Exploiting phrase redundancy and translational relations for phrase table compression
The Prague Bulletin of Mathematical Linguistics | October 2012, Vol 98: pp. 63-74
PSI-toolkit: A Natural Language Processing Pipeline
Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt
Computational Linguistics | April 2012, Vol 458: pp. 27-39
Computational Linguistics
Editor(s): Adam PrzepiórkowskiMaciej PiaseckiKrzysztof JassemPiotr Fuglewicz
Wprowadzenie do metod statystycznych w tłumaczeniu automatycznym
Investigationes Linguisticae | December 2008, Vol 16
Model skończenie stanowy niemieckich wyrazów pojedynczo i wielokrotnie złożonych
Investigationes Linguisticae | June 2007, pp. 50-67