mlsanityData to 14 Oct 2026

Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations

arXiv 2206.14982 ↗First posted 30 Jun 2022cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT training benefit, however, is often limited to many-to-one directions. The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning. Experimenting with the WMT'21 multilingual translation task, we demonstrate that our systems outperform the conventional baselines of direct bilingual models and pivot translation models for most directions, averagely giving +6.0 and +4.1 BLEU, without the need for architecture change or extra data collection. Moreover, we also examine our proposed approach in an extremely large-scale data setting to accommodate practical deployment scenarios.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

19 of 22 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  4. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  5. 2016Sequence-Level Knowledge Distillationcited by 801
  6. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  7. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  8. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  9. 2018Achieving Human Parity on Automatic Chinese to English News Translationcited by 119
  10. 2020Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translationcited by 105
  11. 2019Investigating Multilingual NMT Representations at Scalecited by 68
  12. 2019Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlationscited by 61
7 more
  1. 2016Zero-Resource Translation with Multi-Lingual Neural Machine Translationcited by 46
  2. 2016Multi-Source Neural Translationcited by 37
  3. 2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
  4. 2021Improving Multilingual Translation by Representation and Gradient Regularizationcited by 31
  5. 2020Complete Multilingual Neural Machine Translationcited by 30
  6. 2021An Efficient Transformer Decoder with Compressed Sub-layerscited by 10
  7. 2020Efficient Inference For Neural Machine Translationcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 1.

4 papers.

  1. 2022Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languagescited by 13
  2. 2023Assessing Translation capabilities of Large Language Models involving English and Indian Languagescited by 8
  3. 2023Multilingual Neural Machine Translation System for Indic to Indic Languagescited by 0
  4. 2025Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translationcited by 0