Kenneth Heafield

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