mlsanityData to 7 Oct 2026

The VolcTrans System for WMT22 Multilingual Machine Translation Task

arXiv 2210.11599 ↗First posted 20 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation. We participated in the unconstrained track which allows the use of external resources. Our system is a transformerbased multilingual model trained on data from multiple sources including the public training set from the data track, NLLB data provided by Meta AI, self-collected parallel corpora, and pseudo bitext from back-translation. A series of heuristic rules clean both bilingual and monolingual texts. On the official test set, our system achieves 17.3 BLEU, 21.9 spBLEU, and 41.9 chrF2++ on average over all language pairs. The average inference speed is 11.5 sentences per second using a single Nvidia Tesla V100 GPU. Our code and trained models are available at https://github.com/xian8/wmt22

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

17 of 27 references.

References · 17

  1. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  2. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  3. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  4. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  5. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  6. 2022Towards a Cleaner Document-Oriented Multilingual Crawled Corpuscited by 143
  7. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  8. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
  9. 2017Learning Joint Multilingual Sentence Representations with Neural Machine Translationcited by 52
  10. 2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
  11. 2021Language Tags Matter for Zero-Shot Neural Machine Translationcited by 29
  12. 2021LightSeq2: Accelerated Training for Transformer-based Models on GPUscited by 19
5 more
  1. 2018Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabularycited by 18
  2. 2019Adapting Multilingual Neural Machine Translation to Unseen Languagescited by 12
  3. 2022Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoderscited by 12
  4. 2021Back-translation for Large-Scale Multilingual Machine Translationcited by 11
  5. 2022PARAGEN : A Parallel Generation Toolkitcited by 2

Built on by

Not cited yet.