Google
Google Scholar
Semantic Scholar
MS Academic
CiteSeerX
ORCIDKenneth Heafield
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2020
[c43]Pinzhen Chen, Nikolay Bogoychev, Kenneth Heafield, Faheem Kirefu:
Parallel Sentence Mining by Constrained Decoding. ACL 2020: 1672-1678- [c42]Marta Bañón, Pinzhen Chen, Barry Haddow, Kenneth Heafield, 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, Jaume Zaragoza:
ParaCrawl: Web-Scale Acquisition of Parallel Corpora. ACL 2020: 4555-4567 - [c41]Alham Fikri Aji, Nikolay Bogoychev, Kenneth Heafield, Rico Sennrich:
In Neural Machine Translation, What Does Transfer Learning Transfer? ACL 2020: 7701-7710 - [c40]Kenneth Heafield, Hiroaki Hayashi, Yusuke Oda, Ioannis Konstas, Andrew M. Finch, Graham Neubig, Xian Li, Alexandra Birch:
Findings of the Fourth Workshop on Neural Generation and Translation. NGT@ACL 2020: 1-9 - [c39]Alham Fikri Aji, Kenneth Heafield:
Compressing Neural Machine Translation Models with 4-bit Precision. NGT@ACL 2020: 35-42 - [c38]Nikolay Bogoychev, Roman Grundkiewicz, Alham Fikri Aji, Maximiliana Behnke, Kenneth Heafield, Sidharth Kashyap, Emmanouil-Ioannis Farsarakis, Mateusz Chudyk:
Edinburgh's Submissions to the 2020 Machine Translation Efficiency Task. NGT@ACL 2020: 218-224 - [c37]Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, Kenneth Heafield:
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020. AMTA 2020: 110-115 - [c36]Maximiliana Behnke, Kenneth Heafield:
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation. EMNLP (1) 2020: 2664-2674 - [c35]Ulrich Germann, Roman Grundkiewicz, Martin Popel, Radina Dobreva, Nikolay Bogoychev, Kenneth Heafield:
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task. WMT@EMNLP 2020: 191-196 - [e1]Alexandra Birch, Andrew M. Finch, Hiroaki Hayashi, Kenneth Heafield, Marcin Junczys-Dowmunt, Ioannis Konstas, Xian Li, Graham Neubig, Yusuke Oda:
Proceedings of the Fourth Workshop on Neural Generation and Translation, NGT@ACL 2020, Online, July 5-10, 2020. Association for Computational Linguistics 2020, ISBN 978-1-952148-17-0 [contents] - [i14]Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, Kenneth Heafield:
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020. CoRR abs/2008.04885 (2020) - [i13]Pinzhen Chen, Kenneth Heafield:
Approaching Neural Chinese Word Segmentation as a Low-Resource Machine Translation Task. CoRR abs/2008.05348 (2020) - [i12]Alham Fikri Aji, Kenneth Heafield:
Exploring Monolingual Data for Neural Machine Translation with Knowledge Distillation. CoRR abs/2012.15455 (2020)
2010 – 2019
- 2019
- [c34]Roman Grundkiewicz, Marcin Junczys-Dowmunt, Kenneth Heafield:
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data. BEA@ACL 2019: 252-263 - [c33]Alham Fikri Aji, Kenneth Heafield:
Making Asynchronous Stochastic Gradient Descent Work for Transformers. NGT@EMNLP-IJCNLP 2019: 80-89 - [c32]Anna Currey, Kenneth Heafield:
Zero-Resource Neural Machine Translation with Monolingual Pivot Data. NGT@EMNLP-IJCNLP 2019: 99-107 - [c31]Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev:
From Research to Production and Back: Ludicrously Fast Neural Machine Translation. NGT@EMNLP-IJCNLP 2019: 280-288 - [c30]Alham Fikri Aji, Kenneth Heafield, Nikolay Bogoychev:
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training. EMNLP/IJCNLP (1) 2019: 3624-3629 - [c29]Anna Currey, Kenneth Heafield:
Incorporating Source Syntax into Transformer-Based Neural Machine Translation. WMT (1) 2019: 24-33 - [i11]Alham Fikri Aji, Kenneth Heafield:
Making Asynchronous Stochastic Gradient Descent Work for Transformers. CoRR abs/1906.03496 (2019) - [i10]Alham Fikri Aji, Kenneth Heafield:
Neural Machine Translation with 4-Bit Precision and Beyond. CoRR abs/1909.06091 (2019) - 2018
- [c28]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:
Marian: Fast Neural Machine Translation in C++. ACL (4) 2018: 116-121 - [c27]Roman Grundkiewicz, Kenneth Heafield:
Neural Machine Translation Techniques for Named Entity Transliteration. NEWS@ACL 2018: 89-94 - [c26]Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, Kenneth Heafield:
Fast Neural Machine Translation Implementation. NMT@ACL 2018: 116-121 - [c25]Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue:
Marian: Cost-effective High-Quality Neural Machine Translation in C++. NMT@ACL 2018: 129-135 - [c24]Anna Currey, Kenneth Heafield:
Multi-Source Syntactic Neural Machine Translation. EMNLP 2018: 2961-2966 - [c23]Nikolay Bogoychev, Kenneth Heafield, Alham Fikri Aji, Marcin Junczys-Dowmunt:
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation. EMNLP 2018: 2991-2996 - [c22]Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield:
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task. NAACL-HLT 2018: 595-606 - [c21]Barry Haddow, Nikolay Bogoychev, Denis Emelin, Ulrich Germann, Roman Grundkiewicz, Kenneth Heafield, Antonio Valerio Miceli Barone, Rico Sennrich:
The University of Edinburgh's Submissions to the WMT18 News Translation Task. WMT (shared task) 2018: 399-409 - [c20]Philipp Koehn, Huda Khayrallah, Kenneth Heafield, Mikel L. Forcada:
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering. WMT (shared task) 2018: 726-739 - [i9]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:
Marian: Fast Neural Machine Translation in C++. CoRR abs/1804.00344 (2018) - [i8]Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield:
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task. CoRR abs/1804.05940 (2018) - [i7]Robert V. Lim, Kenneth Heafield, Hieu Hoang, Mark Briers, Allen D. Malony:
Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures. CoRR abs/1805.02094 (2018) - [i6]Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, Kenneth Heafield:
Fast Neural Machine Translation Implementation. CoRR abs/1805.09863 (2018) - [i5]Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue:
Marian: Cost-effective High-Quality Neural Machine Translation in C++. CoRR abs/1805.12096 (2018) - [i4]Nikolay Bogoychev, Marcin Junczys-Dowmunt, Kenneth Heafield, Alham Fikri Aji:
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation. CoRR abs/1808.08859 (2018) - [i3]Anna Currey, Kenneth Heafield:
Multi-Source Syntactic Neural Machine Translation. CoRR abs/1808.10267 (2018) - 2017
- [c19]Alham Fikri Aji, Kenneth Heafield:
Sparse Communication for Distributed Gradient Descent. EMNLP 2017: 440-445 - [c18]Anna Currey, Antonio Valerio Miceli Barone, Kenneth Heafield:
Copied Monolingual Data Improves Low-Resource Neural Machine Translation. WMT 2017: 148-156 - [c17]Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams:
The University of Edinburgh's Neural MT Systems for WMT17. WMT 2017: 389-399 - [i2]Alham Fikri Aji, Kenneth Heafield:
Sparse Communication for Distributed Gradient Descent. CoRR abs/1704.05021 (2017) - [i1]Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams:
The University of Edinburgh's Neural MT Systems for WMT17. CoRR abs/1708.00726 (2017) - 2016
- [c16]Kenneth Heafield, Chase Geigle, Sean Massung, Lane Schwartz:
Normalized Log-Linear Interpolation of Backoff Language Models is Efficient. ACL (1) 2016 - 2015
- [c15]Kenneth Heafield, Rohan Kshirsagar, Santiago Barona:
Language Identification and Modeling in Specialized Hardware. ACL (2) 2015: 384-389 - 2014
- [c14]Kenneth Heafield, Michael Kayser, Christopher D. Manning:
Faster Phrase-Based Decoding by Refining Feature State. ACL (2) 2014: 130-135 - [c13]Christian Buck, Kenneth Heafield, Bas van Ooyen:
N-gram Counts and Language Models from the Common Crawl. LREC 2014: 3579-3584 - [c12]Nadir Durrani, Barry Haddow, Philipp Koehn, Kenneth Heafield:
Edinburgh's Phrase-based Machine Translation Systems for WMT-14. WMT@ACL 2014: 97-104 - [c11]Julia Neidert, Sebastian Schuster, Spence Green, Kenneth Heafield, Christopher D. Manning:
Stanford University's Submissions to the WMT 2014 Translation Task. WMT@ACL 2014: 150-156 - 2013
- [c10]Kenneth Heafield, Ivan Pouzyrevsky, Jonathan H. Clark, Philipp Koehn:
Scalable Modified Kneser-Ney Language Model Estimation. ACL (2) 2013: 690-696 - [c9]Kenneth Heafield, Philipp Koehn, Alon Lavie:
Grouping Language Model Boundary Words to Speed K-Best Extraction from Hypergraphs. HLT-NAACL 2013: 958-968 - [c8]Nadir Durrani, Barry Haddow, Kenneth Heafield, Philipp Koehn:
Edinburgh's Machine Translation Systems for European Language Pairs. WMT@ACL 2013: 114-121 - 2012
- [c7]Kenneth Heafield, Philipp Koehn, Alon Lavie:
Language Model Rest Costs and Space-Efficient Storage. EMNLP-CoNLL 2012: 1169-1178 - 2011
- [c6]Kenneth Heafield, Hieu Hoang, Philipp Koehn, Tetsuo Kiso, Marcello Federico:
Left language model state for syntactic machine translation. IWSLT 2011: 183-190 - [c5]Kenneth Heafield, Alon Lavie:
CMU System Combination in WMT 2011. WMT@EMNLP 2011: 145-151 - [c4]Kenneth Heafield:
KenLM: Faster and Smaller Language Model Queries. WMT@EMNLP 2011: 187-197 - 2010
- [j2]Kenneth Heafield, Alon Lavie:
Combining Machine Translation Output with Open SourceThe Carnegie Mellon Multi-Engine Machine Translation Scheme. Prague Bull. Math. Linguistics 93: 27-36 (2010) - [j1]Jonathan H. Clark, Jonathan Weese, Byung-Gyu Ahn, Andreas Zollmann, Qin Gao, Kenneth Heafield, Alon Lavie:
The Machine Translation Toolpack for LoonyBin: Automated Management of Experimental Machine Translation HyperWorkflows. Prague Bull. Math. Linguistics 93: 117-126 (2010) - [c3]Kenneth Heafield, Alon Lavie:
CMU Multi-Engine Machine Translation for WMT 2010. WMT@ACL 2010: 301-306
2000 – 2009
- 2009
- [c2]Kenneth Heafield, Greg Hanneman, Alon Lavie:
Machine Translation System Combination with Flexible Word Ordering. WMT@EACL 2009: 56-60 - 2008
- [c1]Girish Maskeri Rama, Santonu Sarkar
, Kenneth Heafield:
Mining business topics in source code using latent dirichlet allocation. ISEC 2008: 113-120
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
load content from web.archive.org
Privacy notice: By enabling the option above, your browser will contact the API of web.archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
Tweets on dblp homepage
Show tweets from 
on the dblp homepage.
Privacy notice: By enabling the option above, your browser will contact twitter.com and twimg.com to load tweets curated by our Twitter account. At the same time, Twitter will persistently store several cookies with your web browser. While we did signal Twitter to not track our users by setting the "dnt" flag, we do not have any control over how Twitter uses your data. So please proceed with care and consider checking the Twitter privacy policy.
last updated on 2021-01-21 22:43 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
the dblp computer science bibliography is funded by:
