Kenneth Heafield
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kenneth Heafield has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alham Fikri Aji
School of Informatics University of Edinburgh 10 Crichton Street EH8 9AB Edinburgh Scotland
4 shared publications - Allen D. Malony
University of Oregon
1 shared publication - Anna Currey
University of Edinburgh University of Edinburgh
1 shared publication - Hieu Hoang
The Alan Turing Institute London England U.K
1 shared publication - Marcin Junczys-Dowmunt
Microsoft Azure AI
1 shared publication - Mark Briers
The Alan Turing Institute London England U.K
1 shared publication
Latest Publications
- Open Access
Fully Synthetic Data Improves Neural Machine Translation with Knowledge Distillation
This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate target language monolingual text is to translate it to the source language and round-trip translate it back to the target language, resulting in a fully synthetic corpus. We find that combining monolingual data from both source and target languages yields better performance than a corpus twice as large only in one language. Moreover, experiments reveal that the improvement depends upon the provenance of the test set. If the test set was originally in the source language (with the target side written by translators), then forward translating source monolingual data matters. If the test set was originally in the target language (with the source written by translators), then incorporating target monolingual data matters.
Open AccessFully Synthetic Data Improves Neural Machine Translation with Knowledge Distillation
This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate target language monolingual text is to translate it to the source language and round-trip translate it back to the target language, resulting in a fully synthetic corpus. We find that combining monolingual data from both source and target languages yields better performance than a corpus twice as large only in one language. Moreover, experiments reveal that the improvement depends upon the provenance of the test set. If the test set was originally in the source language (with the target side written by translators), then forward translating source monolingual data matters. If the test set was originally in the target language (with the source written by translators), then incorporating target monolingual data matters.
- Open Access
Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures
Neural machine translation (NMT) has been accelerated by deep learning neural networks over statistical-based approaches, due to the plethora and programmability of commodity heterogeneous computing architectures such as FPGAs and GPUs and the massive amount of training corpuses generated from news outlets, government agencies and social media. Training a learning classifier for neural networks entails tuning hyper-parameters that would yield the best performance. Unfortunately, the number of parameters for machine translation include discrete categories as well as continuous options, which makes for a combinatorial explosive problem. This research explores optimizing hyper-parameters when training deep learning neural networks for machine translation. Specifically, our work investigates training a language model with Marian NMT. Results compare NMT under various hyper-parameter settings across a variety of modern GPU architecture generations in single node and multi-node settings, revealing insights on which hyper-parameters matter most in terms of performance, such as words processed per second, convergence rates, and translation accuracy, and provides insights on how to best achieve high-performing NMT systems.
Open AccessExploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures
Neural machine translation (NMT) has been accelerated by deep learning neural networks over statistical-based approaches, due to the plethora and programmability of commodity heterogeneous computing architectures such as FPGAs and GPUs and the massive amount of training corpuses generated from news outlets, government agencies and social media. Training a learning classifier for neural networks entails tuning hyper-parameters that would yield the best performance. Unfortunately, the number of parameters for machine translation include discrete categories as well as continuous options, which makes for a combinatorial explosive problem. This research explores optimizing hyper-parameters when training deep learning neural networks for machine translation. Specifically, our work investigates training a language model with Marian NMT. Results compare NMT under various hyper-parameter settings across a variety of modern GPU architecture generations in single node and multi-node settings, revealing insights on which hyper-parameters matter most in terms of performance, such as words processed per second, convergence rates, and translation accuracy, and provides insights on how to best achieve high-performing NMT systems.
- Open Access
Neural Machine Translation with 4-Bit Precision and Beyond
Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ logarithmic quantization in lieu of fixed-point quantization. However, we find bias terms are less amenable to log quantization but note they comprise a tiny fraction of the model, so we leave them uncompressed. We also propose to use an error-feedback mechanism during retraining, to preserve the compressed model as a stale gradient. We empirically show that NMT models based on Transformer or RNN architecture can be compressed up to 4-bit precision without any noticeable quality degradation. Models can be compressed up to binary precision, albeit with lower quality. The RNN architecture seems to be more robust to quantization, compared to the Transformer.
Open AccessNeural Machine Translation with 4-Bit Precision and Beyond
Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ logarithmic quantization in lieu of fixed-point quantization. However, we find bias terms are less amenable to log quantization but note they comprise a tiny fraction of the model, so we leave them uncompressed. We also propose to use an error-feedback mechanism during retraining, to preserve the compressed model as a stale gradient. We empirically show that NMT models based on Transformer or RNN architecture can be compressed up to 4-bit precision without any noticeable quality degradation. Models can be compressed up to binary precision, albeit with lower quality. The RNN architecture seems to be more robust to quantization, compared to the Transformer.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 80-89
Making Asynchronous Stochastic Gradient Descent Work for Transformers
Alham Fikri Aji, Kenneth Heafield. Proceedings of the 3rd Workshop on Neural Generation and Translation. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 80-89
Open AccessMaking Asynchronous Stochastic Gradient Descent Work for Transformers
Alham Fikri Aji, Kenneth Heafield. Proceedings of the 3rd Workshop on Neural Generation and Translation. 2019.
- Open Access
Multi-Source Syntactic Neural Machine Translation
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines.
Open AccessMulti-Source Syntactic Neural Machine Translation
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines.
- Open Access
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific training-objective, transfer learning with monolingual data, and ensembling of independently trained GEC models and language models. The combined effects of these methods result in better than state-of-the-art neural GEC models that outperform previously best neural GEC systems by more than 10% M$^2$ on the CoNLL-2014 benchmark and 5.9% on the JFLEG test set. Non-neural state-of-the-art systems are outperformed by more than 2% on the CoNLL-2014 benchmark and by 4% on JFLEG.
Open AccessApproaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific training-objective, transfer learning with monolingual data, and ensembling of independently trained GEC models and language models. The combined effects of these methods result in better than state-of-the-art neural GEC models that outperform previously best neural GEC systems by more than 10% M$^2$ on the CoNLL-2014 benchmark and 5.9% on the JFLEG test set. Non-neural state-of-the-art systems are outperformed by more than 2% on the CoNLL-2014 benchmark and by 4% on JFLEG.
- Open Access
Sparse Communication for Distributed Gradient Descent
We make distributed stochastic gradient descent faster by exchanging sparse updates instead of dense updates. Gradient updates are positively skewed as most updates are near zero, so we map the 99% smallest updates (by absolute value) to zero then exchange sparse matrices. This method can be combined with quantization to further improve the compression. We explore different configurations and apply them to neural machine translation and MNIST image classification tasks. Most configurations work on MNIST, whereas different configurations reduce convergence rate on the more complex translation task. Our experiments show that we can achieve up to 49% speed up on MNIST and 22% on NMT without damaging the final accuracy or BLEU.
Open AccessSparse Communication for Distributed Gradient Descent
We make distributed stochastic gradient descent faster by exchanging sparse updates instead of dense updates. Gradient updates are positively skewed as most updates are near zero, so we map the 99% smallest updates (by absolute value) to zero then exchange sparse matrices. This method can be combined with quantization to further improve the compression. We explore different configurations and apply them to neural machine translation and MNIST image classification tasks. Most configurations work on MNIST, whereas different configurations reduce convergence rate on the more complex translation task. Our experiments show that we can achieve up to 49% speed up on MNIST and 22% on NMT without damaging the final accuracy or BLEU.