Kenneth Heafield

5.9k total citations · 3 hit papers
56 papers, 2.8k citations indexed

About

Kenneth Heafield is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Molecular Biology. According to data from OpenAlex, Kenneth Heafield has authored 56 papers receiving a total of 2.8k indexed citations (citations by other indexed papers that have themselves been cited), including 48 papers in Artificial Intelligence, 13 papers in Computer Vision and Pattern Recognition and 3 papers in Molecular Biology. Recurrent topics in Kenneth Heafield's work include Natural Language Processing Techniques (46 papers), Topic Modeling (45 papers) and Multimodal Machine Learning Applications (12 papers). Kenneth Heafield is often cited by papers focused on Natural Language Processing Techniques (46 papers), Topic Modeling (45 papers) and Multimodal Machine Learning Applications (12 papers). Kenneth Heafield collaborates with scholars based in United Kingdom, United States and Belgium. Kenneth Heafield's co-authors include Philipp Koehn, Jonathan H. Clark, Anna Currey, Roman Grundkiewicz, Marcin Junczys-Dowmunt, Antonio Valerio Miceli Barone, Santonu Sarkar, Alon Lavie, Christopher D. Manning and Barry Haddow and has published in prestigious journals such as Language Resources and Evaluation, Edinburgh Research Explorer (University of Edinburgh) and ePrints Soton (University of Southampton).

In The Last Decade

Kenneth Heafield

53 papers receiving 2.5k citations

Hit Papers

KenLM: Faster and Smaller Language Model Queries 2011 2026 2016 2021 2011 2016 2013 200 400 600

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Kenneth Heafield United Kingdom 22 2.5k 550 311 162 131 56 2.8k
Satanjeev Banerjee United States 12 2.5k 1.0× 1.1k 2.0× 342 1.1× 167 1.0× 114 0.9× 23 3.2k
Rico Sennrich Switzerland 27 2.7k 1.0× 944 1.7× 224 0.7× 131 0.8× 97 0.7× 109 3.1k
Wanxiang Che China 36 3.9k 1.5× 762 1.4× 377 1.2× 211 1.3× 185 1.4× 178 4.3k
Ellie Pavlick United States 23 2.5k 1.0× 540 1.0× 223 0.7× 88 0.5× 62 0.5× 72 2.9k
Daniel Cer United States 26 3.6k 1.4× 641 1.2× 398 1.3× 225 1.4× 98 0.7× 42 4.0k
Fei Huang China 30 2.9k 1.2× 684 1.2× 338 1.1× 195 1.2× 76 0.6× 162 3.4k
Kevin Gimpel United States 22 2.4k 0.9× 395 0.7× 302 1.0× 158 1.0× 121 0.9× 81 2.8k
Noah Constant United States 14 2.1k 0.8× 451 0.8× 275 0.9× 67 0.4× 80 0.6× 22 2.5k
Chengqing Zong China 30 3.4k 1.4× 894 1.6× 388 1.2× 149 0.9× 99 0.8× 249 3.9k
Ivan Vulić United Kingdom 30 2.5k 1.0× 513 0.9× 241 0.8× 136 0.8× 58 0.4× 157 2.8k

Countries citing papers authored by Kenneth Heafield

Since Specialization
Citations

This map shows the geographic impact of Kenneth Heafield's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Kenneth Heafield with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Kenneth Heafield more than expected).

Fields of papers citing papers by Kenneth Heafield

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Kenneth Heafield. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Kenneth Heafield. The network helps show where Kenneth Heafield may publish in the future.

Co-authorship network of co-authors of Kenneth Heafield

This figure shows the co-authorship network connecting the top 25 collaborators of Kenneth Heafield. A scholar is included among the top collaborators of Kenneth Heafield based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Kenneth Heafield. Kenneth Heafield is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Birch, Alexandra, et al.. (2024). Document-Level Machine Translation with Large-Scale Public Parallel Corpora. 13185–13197. 1 indexed citations
2.
Chen, Pinzhen, Barry Haddow, Kenneth Heafield, et al.. (2020). ParaCrawl: Web-Scale Acquisition of Parallel Corpora. ePrints Soton (University of Southampton). 4555–4567. 70 indexed citations
3.
Bogoychev, Nikolay, et al.. (2020). Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task. Edinburgh Research Explorer. 218–224. 3 indexed citations
4.
Heafield, Kenneth, et al.. (2020). Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation. 2664–2674. 28 indexed citations
5.
Germann, Ulrich, et al.. (2020). Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task. Edinburgh Research Explorer (University of Edinburgh). 191–196. 1 indexed citations
6.
Currey, Anna & Kenneth Heafield. (2019). Incorporating Source Syntax into Transformer-Based Neural Machine Translation. Edinburgh Research Explorer (University of Edinburgh). 24–33. 33 indexed citations
7.
Grundkiewicz, Roman, Marcin Junczys-Dowmunt, & Kenneth Heafield. (2019). Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data. Edinburgh Research Explorer (University of Edinburgh). 252–263. 106 indexed citations
9.
Buck, Christian, et al.. (2014). N-gram Counts and Language Models from the Common Crawl. Language Resources and Evaluation. 3579–3584. 77 indexed citations
10.
Durrani, Nadir, Barry Haddow, Philipp Koehn, & Kenneth Heafield. (2014). Edinburgh’s Phrase-based Machine Translation Systems for WMT-14. Workshop on Statistical Machine Translation. 97–104. 1 indexed citations
11.
Heafield, Kenneth, Philipp Koehn, & Arnon Lavie. (2013). Grouping Language Model Boundary Words to Speed K--Best Extraction from Hypergraphs. North American Chapter of the Association for Computational Linguistics. 958–968. 13 indexed citations
12.
Durrani, Nadir, Barry Haddow, Kenneth Heafield, & Philipp Koehn. (2013). Edinburgh's Machine Translation Systems for European Language Pairs. Workshop on Statistical Machine Translation. 114–121. 26 indexed citations
13.
Heafield, Kenneth, et al.. (2013). Scalable Modified Kneser-Ney Language Model Estimation. Meeting of the Association for Computational Linguistics. 690–696. 319 indexed citations breakdown →
14.
Heafield, Kenneth, Philipp Koehn, & Alon Lavie. (2012). Language Model Rest Costs and Space-Efficient Storage. Empirical Methods in Natural Language Processing. 1169–1178. 7 indexed citations
15.
Heafield, Kenneth, Philipp Koehn, & Arnon Lavie. (2012). Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012, July 12-14, 2012, Jeju Island, Korea. 27 indexed citations
16.
Heafield, Kenneth, et al.. (2011). Left language model state for syntactic machine translation.. Edinburgh Research Explorer (University of Edinburgh). 183–190. 13 indexed citations
17.
Heafield, Kenneth. (2011). KenLM: Faster and Smaller Language Model Queries. Workshop on Statistical Machine Translation. 187–197. 710 indexed citations breakdown →
18.
Heafield, Kenneth & Alon Lavie. (2011). CMU System Combination in WMT 2011. Workshop on Statistical Machine Translation. 145–151. 6 indexed citations
19.
Heafield, Kenneth & Alon Lavie. (2011). Proceedings of the Sixth Workshop on Statistical Machine Translation. 9 indexed citations
20.
Heafield, Kenneth & Alon Lavie. (2010). CMU Multi-Engine Machine Translation for WMT 2010. Workshop on Statistical Machine Translation. 301–306. 7 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026