Kenneth Heafield — all works
- No Language Left Behind: Scaling Human-Centered Machine Translation ↗arXiv:2207.04672 · no summary yetNLLB Team et al.2022 · 1,871 citations
- KenLM: Faster and Smaller Language Model QueriesConference on Machine Translation (WMT)Kenneth Heafield2011 · 1,769 citations
- Scalable Modified Kneser-Ney Language Model EstimationAnnual Meeting of the Association for Computational Linguistics (ACL)Kenneth Heafield, Ivan Pouzyrevsky, Jonathan H. Clark, et al.2013 · 716 citations
- Sparse Communication for Distributed Gradient Descent ↗Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · no summary yetAlham Fikri Aji, Kenneth Heafield2017 · 596 citations
- Marian: Fast Neural Machine Translation in C++arXiv:1804.00344Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, et al.2018 · 507 citations
- ParaCrawl: Web-Scale Acquisition of Parallel CorporaAnnual Meeting of the Association for Computational Linguistics (ACL)Marta Bañón, Pinzhen Chen, Barry Haddow, et al.2020 · 312 citations
- Copied Monolingual Data Improves Low-Resource Neural Machine TranslationConference on Machine Translation (WMT)Anna Currey, Antonio Valerio Miceli Barone, Kenneth Heafield2017 · 298 citations
- Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data ↗Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications · no summary yetRoman Grundkiewicz, Marcin Junczys-Dowmunt, Kenneth Heafield2019 · 285 citations
- The University of Edinburgh's Neural MT Systems for WMT17Conference on Machine Translation (WMT)Rico Sennrich, Alexandra Birch, Anna Currey, et al.2017 · 228 citations
- Proceedings of the Association for Computational Linguistics 2014 ↗no summary yetKenneth Heafield, Michael Kayser, Christopher D. Manning2014 · 228 citations
- N-gram Counts and Language Models from the Common CrawlLanguage Resources and Evaluation Conference (LREC)Christian Buck, Kenneth Heafield, Bas van Ooyen2014 · 217 citations
- Findings of the WMT 2018 Shared Task on Parallel Corpus FilteringConference on Machine Translation: Shared Task PapersPhilipp Koehn, Huda Khayrallah, Kenneth Heafield, et al.2018 · 181 citations
- Efficient Methods for Natural Language Processing: A SurveyTransactions of the Association for Computational Linguistics (TACL)Marcos Treviso, Ji-Ung Lee, Tianchu Ji, et al.2023 · 145 citations
- Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task ↗Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · no summary yetMarcin Junczys-Dowmunt et al.2018 · 141 citations
- In Neural Machine Translation, What Does Transfer Learning Transfer? ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetAlham Fikri Aji et al.2020 · 96 citations
- Marian: Cost-effective High-Quality Neural Machine Translation in C++ ↗Proceedings of the 2nd Workshop on Neural Machine Translation and Generation · no summary yetMarcin Junczys-Dowmunt et al.2018 · 94 citations
- Incorporating Source Syntax into Transformer-Based Neural Machine Translation ↗Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers) · no summary yetAnna Currey, Kenneth Heafield2019 · 77 citations
- Iterative Translation Refinement with Large Language ModelsAnnual Conference of the European Association for Machine Translation (EAMT)Pinzhen Chen, Zhicheng Guo, Barry Haddow, et al.2024 · 73 citations
- An Open Dataset and Model for Language IdentificationAnnual Meeting of the Association for Computational Linguistics (ACL)Laurie Burchell, Alexandra Birch, Nikolay Bogoychev, et al.2023 · 60 citations
- Findings of the Fourth Workshop on Neural Generation and Translation ↗Proceedings of the Fourth Workshop on Neural Generation and Translation · no summary yetKenneth Heafield et al.2020 · 35 citations
- Multi-Source Syntactic Neural Machine Translation ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetAnna Currey, Kenneth Heafield2018 · 32 citations
- Left language model state for syntactic machine translation ↗Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign · no summary yetKenneth Heafield et al.2011 · 27 citations
- Proceedings of the Ninth Workshop on Statistical Machine Translation ↗The Association for Computational Linguistics · no summary yetJulia Neidert et al.2014 · 12 citations
- Stanford University's Submissions to the WMT 2014 Translation Task ↗Proceedings of the Ninth Workshop on Statistical Machine Translation · no summary yetJulia Neidert et al.2014 · 11 citations
- Faster Phrase-Based Decoding by Refining Feature State ↗Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yetKenneth Heafield, Michael Kayser, Christopher D. Manning2014 · 7 citations
- The EuroPat Corpus: A Parallel Corpus of European Patent Data ↗Proceedings of the Thirteenth Language Resources and Evaluation Conference · no summary yetKenneth Heafield et al.2022 · 5 citations
This page in Markdown → https://md.research.elamur.ai/free/en/authors/kenneth-heafield/works/