mlsanityData to 14 Oct 2026

Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?

arXiv 2210.11628 ↗First posted 20 Oct 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain and multilingual NMT, particularly for the incomplete data condition where in-domain bitext is missing for some language pairs. Our results in the curated leave-one-domain-out experiments show that multi-domain multilingual (MDML) NMT can boost zero-shot translation performance up to +10 gains on BLEU, as well as aid the generalisation of multi-domain NMT to the missing domain. We also explore strategies for effective integration of multilingual and multi-domain NMT, including language and domain tag combination and auxiliary task training. We find that learning domain-aware representations and adding target-language tags to the encoder leads to effective MDML-NMT.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

21 of 34 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  5. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  6. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  7. 2017Six Challenges for Neural Machine Translationcited by 335
  8. 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 257
  9. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 242
  10. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  11. 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
  12. 2021Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inferencecited by 96
9 more
  1. 2016Toward Multilingual Neural Machine Translation with Universal Encoder and Decodercited by 76
  2. 2020Analyzing the Source and Target Contributions to Predictions in Neural Machine Translationcited by 71
  3. 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
  4. 2016Domain Control for Neural Machine Translationcited by 36
  5. 2016Fast Domain Adaptation for Neural Machine Translationcited by 28
  6. 2021Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapterscited by 21
  7. 2019Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networkscited by 12
  8. 2019Improving Domain Adaptation Translation with Domain Invariant and Specific Informationcited by 7
  9. 2020A Multilingual Neural Machine Translation Model for Biomedical Datacited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?cited by 2