mlsanityData to 7 Oct 2026

From Bilingual to Multilingual Neural Machine Translation by Incremental Training

arXiv 1907.00735 ↗First posted 28 Jun 2019cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that allows the system to scale to more languages without modification of the previous components based on joint training and language-independent encoder/decoder modules allowing for zero-shot translation. This work in progress shows close results to the state-of-the-art in the WMT task.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 1; 2023: 3; 2024: 5.

14 papers.

Sort:

  1. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  2. 2021Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitutioncited by 31
  3. 2023Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lenscited by 15
  4. 2021Continual Learning in Multilingual NMT via Language-Specific Embeddingscited by 12
  5. 2021How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translationcited by 11
  6. 2022Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillationcited by 5
  7. 2024Self-generated Replay Memories for Continual Neural Machine Translationcited by 4
  8. 2021Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoderscited by 3
  9. 2023Multilingual k-Nearest-Neighbor Machine Translationcited by 3
  10. 2023Efficiently Upgrading Multilingual Machine Translation Models to Support More Languagescited by 2
  11. 2024Forklift: An Extensible Neural Liftercited by 2
  12. 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddingscited by 1
2 more
  1. 2024How effective is Multi-source pivoting for Translation of Low Resource Indian Languages?cited by 1
  2. 2024Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languagescited by 0