Papers
- Cheat Codes to Quantify Missing Source Information in Neural Machine Translation
Proyag Pal and . NAACL, Seattle, Washington, 10—15 July, 2022.
[Paper] [BibTeX] - Exploring Diversity in Back Translation for Low-Resource Machine Translation
Laurie Burchell, Alexandra Birch, and . DeepLo at NAACL, Seattle, Washington, 14 July, 2022.
[Paper] [BibTeX] - The EuroPat Corpus: A Parallel Corpus of European Patent Data
, Elaine Farrow, Jelmer van der Linde, Gema Ramírez-Sánchez, and Dion Wiggins. LREC, Marseille, France, 20—25 June, 2022.
[Paper] [Corpus] [BibTeX]
- TranslateLocally: Blazing-fast translation running on the local CPU
Nikolay Bogoychev, Jelmer van der Linde, and . EMNLP, Punta Cana, Dominican Republic, 7—9 November, 2021.
[Paper] [Software] [BibTeX] - Findings of the 2021 Conference on Machine Translation (WMT21)
Farhad Akhbardeh, Arkady Arkhangorodsky, Magdalena Biesialska, Ondřej Bojar, Rajen Chatterjee, Vishrav Chaudhary, Marta R. Costa-jussa, Cristina España-Bonet, Angela Fan, Christian Federmann, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Leonie Harter, , Christopher Homan, Matthias Huck, Kwabena Amponsah-Kaakyire, Jungo Kasai, Daniel Khashabi, Kevin Knight, Tom Kocmi, Philipp Koehn, Nicholas Lourie, Christof Monz, Makoto Morishita, Masaaki Nagata, Ajay Nagesh, Toshiaki Nakazawa, Matteo Negri, Santanu Pal, Allahsera Auguste Tapo, Marco Turchi, and Valentin Vydrin and Marcos Zampieri. WMT at EMNLP, Punta Cana, Dominican Republic, 10—11 November, 2021.
[Paper] [BibTeX] - Findings of the WMT 2021 Shared Task on Efficient Translation
, Qianqian Zhu, and Roman Grundkiewicz. WMT at EMNLP, Punta Cana, Dominican Republic, 10—11 November, 2021.
[Paper] [Slides] [Blog] [Raw results] [BibTeX] - Efficient Machine Translation with Model Pruning and Quantization
Maximiliana Behnke, Nikolay Bogoychev, Alham Fikri Aji, , Graeme Nail, Qianqian Zhu, Svetlana Tchistiakova, Jelmer van der Linde, Pinzhen Chen, Sidharth Kashyap, and Roman Grundkiewicz. WMT at EMNLP, Punta Cana, Dominican Republic, 10—11 November, 2021.
[Paper] [BibTeX] - The University of Edinburgh's English-German and English-Hausa Submissions to the WMT21 News Translation Task
Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell, Nikolay Bogoychev, Antonio Valerio Miceli Barone, Jonas Waldendorf, Alexandra Birch, and . WMT at EMNLP, Punta Cana, Dominican Republic, 10—11 November, 2021.
[Paper] [BibTeX] - Pruning Neural Machine Translation for Speed Using Group Lasso
Maximiliana Behnke and . WMT at EMNLP, Punta Cana, Dominican Republic, 10—11 November, 2021.
[Paper] [BibTeX] - Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Adithya Renduchintala, Denise Diaz, , Xian Li, and Mona Diab. ACL, Online, 2—4 August, 2021.
[Paper] [BibTeX]
- Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
Ulrich Germann, Roman Grundkiewicz, Martin Popel, Radina Dobreva, Nikolay Bogoychev, and . WMT at EMNLP, Online, 19—20 November, 2020.
[Paper] [BibTeX] - Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation
Maximiliana Behnke and . EMNLP, Online, 16—18 November, 2020.
[Paper] [BibTeX] - The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, and . AMTA, Virtual, 5—9 October, 2020.
[Paper] [BibTeX] - Compressing Neural Machine Translation Models with 4-bit Precision
Alham Fikri Aji and . WNGT at ACL, Online, 9—10 July, 2020.
[Paper] [BibTeX] - Edinburgh's Submissions to the 2020 Machine Translation Efficiency Task
Nikolay Bogoychev, Roman Grundkiewicz, Alham Fikri Aji, Maximiliana Behnke, , Sidharth Kashyap, Emmanouil-Ioannis Farsarakis, and Mateusz Chudyk. WNGT at ACL, Online, 9—10 July, 2020.
[Paper] [Raw results] [BibTeX] - Findings of the Fourth Workshop on Neural Generation and Translation
, Hiroaki Hayashi, Yusuke Oda, Ioannis Konstas, Andrew Finch, Graham Neubig, Xian Li, and Alexandra Birch. WNGT at ACL, Online, 9—10 July, 2020.
[Paper] [Slides] [Raw results] [BibTeX] - In Neural Machine Translation, What Does Transfer Learning Transfer?
Alham Fikri Aji, Nikolay Bogoychev, , and Rico Sennrich. ACL, Online, 6 July, 2020.
[Paper] [BibTeX] - Parallel Sentence Mining by Constrained Decoding
Pinzhen Chen, Nikolay Bogoychev, , and Faheem Kirefu. ACL, Online, 6 July, 2020.
[Paper] [BibTeX] - ParaCrawl: Web-Scale Acquisition of Parallel Corpora
Marta Bañón, Pinzhen Chen, Barry Haddow, , Hieu Hoang, Miquel Esplà-Gomis, Mikel L. Forcada, Amir Kamran, Faheem Kirefu, Philipp Koehn, Sergio Ortiz Rojas, Leopoldo Pla Sempere, Gema Ramírez-Sánchez, Elsa Sarrías, Marek Strelec, Brian Thompson, William Waites, Dion Wiggins, and Jaume Zaragoza. ACL, Online, 6 July, 2020.
[Paper] [Corpus] [BibTeX]
- From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, , Roman Grundkiewicz, and Nikolay Bogoychev. WNGT at EMNLP, Hong Kong, 4 November, 2019.
[Paper] [BibTeX] - Zero-Resource Neural Machine Translation with Monolingual Pivot Data
Anna Currey and . WNGT at EMNLP, Hong Kong, 4 November, 2019.
[Paper] [BibTeX] - Making Asynchronous Stochastic Gradient Descent Work for Transformers
Alham Fikri Aji and . WNGT at EMNLP, Hong Kong, 4 November, 2019.
[Paper] [BibTeX] - Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training
Alham Fikri Aji, , and Nikolay Bogoychev. EMNLP-IJCNLP, Hong Kong, 5—7 November, 2019.
[Paper] [BibTeX] - Incorporating Source Syntax into Transformer-Based Neural Machine Translation
Anna Currey and . WMT at ACL, Florence, Italy, 1—2 August, 2019.
[Paper] [BibTeX] - Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data
Roman Grundkiewicz, Marcin Junczys-Dowmunt, and . BEA at ACL, Florence, Italy, 2 August, 2019.
[Paper] [BibTeX] - Surprise Languages: Rapid-Response Cross-Language IR
Douglas Oard, Petra Galuscakova, Kathleen McKeown, Marine Carpuat, Ramy Eskander, , Efsun Kayi, Chris Kedzie, Smaranda Muresan, Suraj Nair, Xing Niu, Dragomir Radev, Anton Ragni, Han-Chin Shing, Yan Virin, Weijia Xu, Rui Zhang, Elena Zotkina, Joseph Barrow, and Mark Gales. EVIA, Tokyo, Japan, 10 June, 2019.
[Paper] [BibTeX]
- Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering
Philipp Koehn, Huda Khayrallah, , and Mikel L. Forcada. WMT at EMNLP, Brussels, Belgium, 31 October, 2018.
[Paper] [BibTeX] - The University of Edinburgh's Submissions to the WMT18 News Translation Task
Barry Haddow, Nikolay Bogoychev, Denis Emelin, Ulrich Germann, Roman Grundkiewicz, , Antonio Valerio Miceli Barone, and Rico Sennrich. WMT at EMNLP, Brussels, Belgium, 31 October, 2018.
[Paper] [BibTeX] - Multi-Source Syntactic Neural Machine Translation
Anna Currey and . EMNLP, Brussels, Belgium, 2—4 November, 2018.
[Paper] [BibTeX] - Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation
Nikolay Bogoychev, Marcin Junczys-Dowmunt, , and Alham Fikri Aji. EMNLP, Brussels, Belgium, 2—4 November, 2018.
[Paper] [BibTeX] - Marian: Cost-effective High-Quality Neural Machine Translation in C++
Marcin Junczys-Dowmunt, , Hieu Hoang, Roman Grundkiewicz, and Anthony Aue. WNMT, Melbourne, Australia, 20 July, 2018.
[Paper] [BibTeX] - Neural Machine Translation Techniques for Named Entity Transliteration
Roman Grundkiewicz and . NEWS, Melbourne, Australia, 20 July, 2018.
[Paper] [BibTeX] - Fast Neural Machine Translation Implementation
Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, and . WNMT, Melbourne, Australia, 20 July, 2018.
[Paper] [BibTeX] - Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation
Anna Currey and . RELNLP, Melbourne, Australia, 19 July, 2018.
[Paper] [BibTeX] - Marian: Fast Neural Machine Translation in C++
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, , Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, and Alexandra Birch. ACL Demos, Melbourne, Australia, 15—20 July, 2018.
[Paper] [BibTeX] - Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, and . NAACL, New Orleans, Louisiana, 1—6 June, 2018.
[Paper] [BibTeX]
- Sparse Communication for Distributed Gradient Descent
Alham Fikri Aji and . EMNLP, Copenhagen, Denmark, 9—11 September, 2017.
[Paper] [BibTeX] - Copied Monolingual Data Improves Low-Resource Neural Machine Translation
Anna Currey, Antonio Valerio Miceli Barone, and . WMT at EMNLP, Copenhagen, Denmark, 7—8 September, 2017.
[Paper] [BibTeX] - The University of Edinburgh’s Neural MT Systems for WMT17
Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, , Antonio Valerio Miceli Barone, and Philip Williams. WMT at EMNLP, Copenhagen, Denmark, 7—8 September, 2017.
[Paper] [BibTeX]
- Normalized Log-Linear Language Model Interpolation is Efficient
, Chase Geigle, Sean Massung, and Lane Schwartz. ACL, Berlin, Germany, 8—10 August, 2016.
[Paper] [BibTeX]
- Language Identification and Modeling in Specialized Hardware
, Rohan Kshirsagar, and Santiago Barona. ACL, Beijing, China, 26—31 July, 2015.
[Paper] [BibTeX]
- Edinburgh’s Phrase-based Machine Translation Systems for WMT-14
Nadir Durrani, Barry Haddow, Philipp Koehn, and . WMT at ACL, Baltimore, MD, USA, 26—27 June, 2014.
[Paper] [BibTeX] - Stanford University’s Submissions to the WMT 2014 Translation Task
Julia Neidert, Sebastian Schuster, Spence Green, , and Christopher D. Manning. WMT at ACL, Baltimore, MD, USA, 26—27 June, 2014.
[Paper] [BibTeX] - Faster Phrase-Based Decoding by Refining Feature State
, Michael Kayser, and Christopher D. Manning. ACL, Baltimore, MD, USA, 22—25 June, 2014.
[Paper] [Code] [BibTeX] - N-gram Counts and Language Models from the Common Crawl
Christian Buck, , and Bas van Ooyen. LREC, Reykjavík, Iceland, 26—31 May, 2014.
[Paper] [BibTeX]
- Efficient Language Modeling Algorithms with Applications to Statistical Machine Translation
. PhD Thesis Committee: Alon Lavie, Chris Dyer, Bhiksha Raj, and Philipp Koehn. 20 September, 2013.
[Paper] [Slides] [BibTeX] - Edinburgh's Machine Translation Systems for European Language Pairs
Nadir Durrani, Barry Haddow, , and Philipp Koehn. WMT at ACL, Sofia, Bulgaria, 8—9 August, 2013.
[Paper] [BibTeX] - Scalable Modified Kneser-Ney Language Model Estimation
, Ivan Pouzyrevsky, Jonathan H. Clark, and Philipp Koehn. ACL, Sofia, Bulgaria, 4—7 August, 2013.
[Paper] [Slides] [Code] [BibTeX] - Grouping Language Model Boundary Words to Speed K-Best Extraction from Hypergraphs
, Philipp Koehn, and Alon Lavie. NAACL HLT, Atlanta, Georgia, USA, 10—12 June, 2013.
[Paper] [Slides] [Code] [BibTeX]
- Language Model Rest Costs and Space-Efficient Storage
, Philipp Koehn, and Alon Lavie. EMNLP, Jeju Island, Korea, 12—14 July, 2012.
[Paper] [Slides] [BibTeX] - Identification of Topics in Source Code
Girish Maskeri Rama, , and Santonu Sarkar. US Patent 8209665 filed in 2009 and issued 26 June, 2012.
[Patent] [BibTeX]
- Left Language Model State for Syntactic Machine Translation
, Hieu Hoang, Philipp Koehn, Tetsuo Kiso, and Marcello Federico. IWSLT, San Francisco, California, USA, 8—9 December, 2011.
[Paper] [Poster] [BibTeX] - KenLM: Faster and Smaller Language Model Queries
. WMT at EMNLP, Edinburgh, Scotland, United Kingdom, 30—31 July, 2011.
[Paper] [Slides] [Code] [BibTeX] - CMU System Combination in WMT 2011
and Alon Lavie. WMT at EMNLP, Edinburgh, Scotland, United Kingdom, 30—31 July, 2011.
[Paper] [Slides] [BibTeX] - Systems and Methods for Identifying Similar Documents
Taylor Curtis and . US Patent 7958136 filed in 2008 and issued 7 June, 2011.
[Patent] [BibTeX]
- Voting on N-grams for Machine Translation System Combination
and Alon Lavie. AMTA, Denver, Colorado, USA, November, 2010.
[Paper] [BibTeX] - CMU Multi-Engine Machine Translation for WMT 2010
and Alon Lavie. WMT at ACL, Uppsala, Sweden, July, 2010.
[Paper] [Poster] [BibTeX] - Combining Machine Translation Output with Open Source: The Carnegie Mellon Multi-Engine Machine Translation Scheme
and Alon Lavie. The Prague Bulletin of Mathematical Linguistics 93. 25—30 January, 2010.
[Paper] [Slides] [BibTeX] - The Machine Translation Toolpack for LoonyBin: Automated Management of Experimental Machine Translation HyperWorkflows
Jonathan H. Clark, Jonathan Weese, Byung Gyu Ahn, Andreas Zollmann, Qin Gao, , and Alon Lavie. The Prague Bulletin of Mathematical Linguistics 93. 25—30 January, 2010.
[Paper] [BibTeX]
- CMU-StatXfer Group System Combination
. NIST Open MT Workshop at MT Summit XII, Ottawa, Canada, 1 September, 2009.
[Description] [Slides] [BibTeX]1 - Machine Translation System Combination with Flexible Word Ordering
, Greg Hanneman, and Alon Lavie. WMT at EACL, Athens, Greece, 30—31 March, 2009.
[Paper] [Slides] [BibTeX]
- 10-year test of time award.
Mining Business Topics in Source Code using Latent Dirichlet Allocation
Girish Maskeri, Santonu Sarkar, and . 1st India Software Engineering Conference, Hyderabad, India, 19—22 February, 2008.
[Paper] [BibTeX]2
- RR Lyrae Stars in the Far Ultraviolet: GALEX Observations Compared with Theoretical Predictions
Stanley Browne, Jonathan Wheatley, Barry Welsh, Mark Seibert, , R. Michael Rich, and the GALEX Science Team. American Astronomical Society 207th Meeting, Washington, DC, USA, 8—12 June, 2006.
[Poster] [BibTeX]
- The GALEX Ultraviolet Variability Catalog
Barry Welsh, Johathan Wheatley, , Mark Seibert, and the GALEX Science Team. The Astronomical Journal 130. 2005.
[Paper] [BibTeX] - The Flaring UV Sky
Barry Welsh, Jonathan Wheatley, , Mark Seibert, Stanley Browne, and the GALEX Science Team. American Astronomical Society 205th Meeting, San Diego, California, USA, 9—13 January, 2005.
[Poster] [BibTeX]
