mlsanityData to 7 Oct 2026

Back-translation for Large-Scale Multilingual Machine Translation

arXiv 2109.08712 ↗First posted 17 Sep 2021cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a hypothesis that a universal cross-language representation leads to better multilingual translation performance. We extend the exploration of different back-translation methods from bilingual translation to multilingual translation. Better performance is obtained by the constrained sampling method, which is different from the finding of the bilingual translation. Besides, we also explore the effect of vocabularies and the amount of synthetic data. Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement. We submitted to both the small tasks and achieved the second place.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 17 Sep 2021.

Builds on

17 of 20 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  3. 2018Hierarchical Neural Story Generationcited by 1,182
  4. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  5. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  6. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  7. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  8. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  9. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  10. 2019Massively Multilingual Neural Machine Translationcited by 246
  11. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  12. 2019Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabulariescited by 27
5 more
  1. 2019Generalizing Back-Translation in Neural Machine Translationcited by 18
  2. 2017Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languagescited by 10
  3. 2019Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translationcited by 8
  4. 2020Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoderscited by 8
  5. 2017Improving a Multi-Source Neural Machine Translation Model with Corpus Extension for Low-Resource Languagescited by 4

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4; 2025: 1.

11 papers.

  1. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  2. 2025Enhancing LLM Safety Through a Theoretical Minimax Game Lenscited by 18
  3. 2023Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lenscited by 15
  4. 2023Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translationcited by 5
  5. 2024Backdoor Attack on Multilingual Machine Translationcited by 5
  6. 2022Learning an Artificial Language for Knowledge-Sharing in Multilingual Translationcited by 4
  7. 2023Ask Language Model to Clean Your Noisy Translation Datacited by 3
  8. 2024IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translationcited by 3
  9. 2024Low-Resource Machine Translation through the Lens of Personalized Federated Learningcited by 1
  10. 2022The VolcTrans System for WMT22 Multilingual Machine Translation Taskcited by 0
  11. 2022University of Cape Town's WMT22 System: Multilingual Machine Translation for Southern African Languagescited by 0