# The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

arXiv: https://arxiv.org/abs/2008.04885 · HTML: https://mlsanity.com/paper/2008.04885/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 16 of 16)

- [Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation](https://mlsanity.com/paper/2105.08504/) (2021)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models](https://mlsanity.com/paper/2201.08471/) (2022)
- [CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality](https://mlsanity.com/paper/2205.04022/) (2022)
- [Neural Approaches to Multilingual Information Retrieval](https://mlsanity.com/paper/2209.01335/) (2022)
- [C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval](https://mlsanity.com/paper/2204.11989/) (2022)
- [A baseline revisited: Pushing the limits of multi-segment models for context-aware translation](https://mlsanity.com/paper/2210.10906/) (2022)
- [Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation](https://mlsanity.com/paper/2105.15087/) (2021)
- [Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions](https://mlsanity.com/paper/2210.05047/) (2022)
- [On Biasing Transformer Attention Towards Monotonicity](https://mlsanity.com/paper/2104.03945/) (2021)
- [Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study](https://mlsanity.com/paper/2404.08259/) (2024)
- [Machine Translation Impact in E-commerce Multilingual Search](https://mlsanity.com/paper/2302.00119/) (2023)
- [The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation](https://mlsanity.com/paper/2205.06618/) (2022)
- [Sockeye 3: Fast Neural Machine Translation with PyTorch](https://mlsanity.com/paper/2207.05851/) (2022)
- [Distillation for Multilingual Information Retrieval](https://mlsanity.com/paper/2405.00977/) (2024)
- [Faithful Target Attribute Prediction in Neural Machine Translation](https://mlsanity.com/paper/2109.12105/) (2021)

## Abstract (arXiv)

We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.