The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
Not on the map. Why?
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.
Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 8; 2023: 1; 2024: 2.
16 papers.
Sort:
By area:
- 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
- 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36
- 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formalitycited by 24
- 2022Neural Approaches to Multilingual Information Retrievalcited by 18
- 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrievalcited by 14
- 2022A baseline revisited: Pushing the limits of multi-segment models for context-aware translationcited by 11
- 2021Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translationcited by 9
- 2022Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactionscited by 7
- 2021On Biasing Transformer Attention Towards Monotonicitycited by 5
- 2024Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Studycited by 5
- 2023Machine Translation Impact in E-commerce Multilingual Searchcited by 4
4 more
- 2022The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translationcited by 3
- 2022Sockeye 3: Fast Neural Machine Translation with PyTorchcited by 3
- 2024Distillation for Multilingual Information Retrievalcited by 3
- 2021Faithful Target Attribute Prediction in Neural Machine Translationcited by 2
- 2024Distillation for Multilingual Information Retrieval2 May 2024
- 2024Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study12 Apr 2024
- 2023Machine Translation Impact in E-commerce Multilingual Search31 Jan 2023
- 2022A baseline revisited: Pushing the limits of multi-segment models for context-aware translation19 Oct 2022
- 2022Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions10 Oct 2022
- 2022Neural Approaches to Multilingual Information Retrieval3 Sep 2022
- 2022Sockeye 3: Fast Neural Machine Translation with PyTorch12 Jul 2022
- 2022The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation13 May 2022
- 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality9 May 2022
- 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval25 Apr 2022
- 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models20 Jan 2022
- 2021Faithful Target Attribute Prediction in Neural Machine Translation24 Sep 2021
4 more
- 2021Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation31 May 2021
- 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation18 May 2021
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfer8 Apr 2021
- 2021On Biasing Transformer Attention Towards Monotonicity8 Apr 2021
- 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
- 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
- 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36
- 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formalitycited by 24
- 2022Neural Approaches to Multilingual Information Retrievalcited by 18
- 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrievalcited by 14
- 2022A baseline revisited: Pushing the limits of multi-segment models for context-aware translationcited by 11
- 2021Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translationcited by 9
- 2021On Biasing Transformer Attention Towards Monotonicitycited by 5
- 2024Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Studycited by 5
- 2023Machine Translation Impact in E-commerce Multilingual Searchcited by 4
- 2022The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translationcited by 3
12 most cited of 15 All 15 (JSON)
- 2024Distillation for Multilingual Information Retrieval2 May 2024
- 2024Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study12 Apr 2024
- 2023Machine Translation Impact in E-commerce Multilingual Search31 Jan 2023
- 2022A baseline revisited: Pushing the limits of multi-segment models for context-aware translation19 Oct 2022
- 2022Neural Approaches to Multilingual Information Retrieval3 Sep 2022
- 2022Sockeye 3: Fast Neural Machine Translation with PyTorch12 Jul 2022
- 2022The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation13 May 2022
- 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality9 May 2022
- 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval25 Apr 2022
- 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models20 Jan 2022
- 2021Faithful Target Attribute Prediction in Neural Machine Translation24 Sep 2021
- 2021Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation31 May 2021
12 newest of 15 All 15 (JSON)