← Authors

Kenneth Heafield

52 papers · 2012–2024 · 7 conferences · across top CS/AI conferences

Achievements

๐Ÿ—บ๏ธ Taxonomy Completionist (68) ๐ŸŒ Conference Polyglot (7) ๐ŸŒˆ Renaissance Researcher (8) ๐ŸŒ‰ Interdisciplinary Bridge ๐Ÿ Cross-Pollinator (5) ๐Ÿฃ Hot Topic Early Bird ๐Ÿงญ Keyword Pioneer ๐Ÿƒ Academic Marathon (12) ๐ŸŒŸ Keyword Trendsetter Combo (5) ๐Ÿ  Conference Loyalist (20) ๐Ÿ”ฌ Deep Specialist (34) ๐Ÿงฌ Topic Evolution ๐Ÿ‘ฅ Mega-Team (36) ๐Ÿ† Keyword Champion (3) ๐Ÿค Dynamic Duo (17) ๐Ÿ—ƒ๏ธ Keyword Collector (184) โšก Prolific Year (8) ๐Ÿ”ฅ Unstoppable (13) ๐Ÿ“ˆ Trend Setter ๐Ÿ’Ž Century Club (52) โ“ The Questioner

Conferences

ACL (20) EMNLP (20) NAACL (4) EACL (3) IJCNLP (3) COLING (1) CONLL (1)

Top co-authors

Nikolay Bogoychev (17) Roman Grundkiewicz (12) Alham Fikri Aji (11) Alexandra Birch (7) Philipp Koehn (7) Marcin Junczys-Dowmunt (6) Maximiliana Behnke (5) Pinzhen Chen (5) Laurie Burchell (4) Jelmer van der Linde (4)

Keywords

neural machine translation (31) model compression (9) machine translation (8) knowledge distillation (5) stochastic gradient descent (5) distributed learning (4) transformer model (4) efficient inference (4) low-resource translation (3) distributed training (3) efficient translation (3) model convergence (3) model pruning (3) translation quality (3) model quantization (3) throughput optimization (3) transformer architecture (3) low-resource language (3) gradient compression (3) latency optimization (3)

Papers

Code-Switched Language Identification is Harder Than You Think EACL 2024
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca EACL 2024
Document-Level Machine Translation with Large-Scale Public Parallel Corpora ACL 2024
Cheating to Identify Hard Problems for Neural Machine Translation EACL 2023
An Open Dataset and Model for Language Identification ACL 2023
Exploring diversity in back translation for low-resource machine translation NAACL 2022
Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization COLING 2022
Findings of the WMT 2022 Shared Task on Efficient Translation EMNLP 2022
Edinburghโ€™s Submission to the WMT 2022 Efficiency Task EMNLP 2022
Cheat Codes to Quantify Missing Source Information in Neural Machine Translation NAACL 2022
TranslateLocally: Blazing-fast translation running on the local CPU EMNLP 2021
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation IJCNLP 2021
Pruning Neural Machine Translation for Speed Using Group Lasso EMNLP 2021
Efficient Machine Translation with Model Pruning and Quantization EMNLP 2021
Findings of the WMT 2021 Shared Task on Efficient Translation EMNLP 2021
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation ACL 2021
The University of Edinburghโ€™s English-German and English-Hausa Submissions to the WMT21 News Translation Task EMNLP 2021
Findings of the 2021 Conference on Machine Translation (WMT21) EMNLP 2021
Findings of the Fourth Workshop on Neural Generation and Translation ACL 2020
In Neural Machine Translation, What Does Transfer Learning Transfer? ACL 2020
ParaCrawl: Web-Scale Acquisition of Parallel Corpora ACL 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 EMNLP 2020
Parallel Sentence Mining by Constrained Decoding ACL 2020
Compressing Neural Machine Translation Models with 4-bit Precision ACL 2020
Edinburghโ€™s Submissions to the 2020 Machine Translation Efficiency Task ACL 2020
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation EMNLP 2020
Making Asynchronous Stochastic Gradient Descent Work for Transformers EMNLP 2019
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data ACL 2019
Incorporating Source Syntax into Transformer-Based Neural Machine Translation ACL 2019
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training EMNLP 2019
Zero-Resource Neural Machine Translation with Monolingual Pivot Data EMNLP 2019
From Research to Production and Back: Ludicrously Fast Neural Machine Translation EMNLP 2019
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training IJCNLP 2019
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task NAACL 2018
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation EMNLP 2018
Multi-Source Syntactic Neural Machine Translation EMNLP 2018
Marian: Cost-effective High-Quality Neural Machine Translation in C++ ACL 2018
Fast Neural Machine Translation Implementation ACL 2018
Neural Machine Translation Techniques for Named Entity Transliteration ACL 2018
Marian: Fast Neural Machine Translation in C++ ACL 2018
Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation ACL 2018
The University of Edinburghโ€™s Submissions to the WMT18 News Translation Task EMNLP 2018
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering EMNLP 2018
Sparse Communication for Distributed Gradient Descent EMNLP 2017
Normalized Log-Linear Interpolation of Backoff Language Models is Efficient ACL 2016
Language Identification and Modeling in Specialized Hardware ACL 2015
Language Identification and Modeling in Specialized Hardware IJCNLP 2015
Faster Phrase-Based Decoding by Refining Feature State ACL 2014
Grouping Language Model Boundary Words to Speed Kโ€“Best Extraction from Hypergraphs NAACL 2013
Scalable Modified Kneser-Ney Language Model Estimation ACL 2013
Language Model Rest Costs and Space-Efficient Storage EMNLP 2012
Language Model Rest Costs and Space-Efficient Storage CONLL 2012