mlsanityData to 7 Oct 2026

Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages

arXiv 2210.09644 ↗First posted 18 Oct 2022cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper describes Tencent's multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages. We participated in the constrained translation track in which only the data and pretrained models provided by the organizer are allowed. The task is challenging due to three problems, including the absence of training data for some to-be-evaluated language pairs, the uneven optimization of language pairs caused by data imbalance, and the curse of multilinguality. To address these problems, we adopt data augmentation, distributionally robust optimization, and language family grouping, respectively, to develop our multilingual neural machine translation (MNMT) models. Our submissions won the 1st place on the blind test sets in terms of the automatic evaluation metrics. Codes, models, and detailed competition results are available at https://github.com/wxjiao/WMT2022-Large-Scale-African.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

21 of 27 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  6. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  7. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  8. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  9. 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 253
  10. 2019Distributionally Robust Language Modelingcited by 142
  11. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  12. 2019Tagged Back-Translationcited by 76
9 more
  1. 2020Balancing Training for Multilingual Neural Machine Translationcited by 71
  2. 2020Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translationcited by 51
  3. 2020Multi-task Learning for Multilingual Neural Machine Translationcited by 46
  4. 2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
  5. 2021Distributionally Robust Multilingual Machine Translationcited by 18
  6. 2020Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translationcited by 17
  7. 2021Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translationcited by 17
  8. 2022Understanding and Mitigating the Uncertainty in Zero-Shot Translationcited by 9
  9. 2022Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translationscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 3; 2025: 2.

13 papers.

Sort:

  1. 2023Is ChatGPT A Good Translator? Yes With GPT-4 As The Enginecited by 172
  2. 2023BiasAsker: Measuring the Bias in Conversational AI Systemcited by 52
  3. 2023Exploring Human-Like Translation Strategy with Large Language Modelscited by 44
  4. 2023ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedbackcited by 34
  5. 2023MTTM: Metamorphic Testing for Textual Content Moderation Softwarecited by 20
  6. 2024Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directionscited by 12
  7. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  8. 2022Adapters for Enhanced Modeling of Multilingual Knowledge and Textcited by 5
  9. 2023Validating Multimedia Content Moderation Software via Semantic Fusioncited by 5
  10. 2024DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimizationcited by 5
  11. 2023An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Softwarecited by 3
  12. 2024NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Taskcited by 0
1 more
  1. 2025Metamorphic Testing for Audio Content Moderation Softwarecited by 0