mlsanityData to 14 Oct 2026

Flow-Adapter Architecture for Unsupervised Machine Translation

arXiv 2204.12225 ↗First posted 26 Apr 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a flow-adapter architecture for unsupervised NMT. It leverages normalizing flows to explicitly model the distributions of sentence-level latent representations, which are subsequently used in conjunction with the attention mechanism for the translation task. The primary novelties of our model are: (a) capturing language-specific sentence representations separately for each language using normalizing flows and (b) using a simple transformation of these latent representations for translating from one language to another. This architecture allows for unsupervised training of each language independently. While there is prior work on latent variables for supervised MT, to the best of our knowledge, this is the first work that uses latent variables and normalizing flows for unsupervised MT. We obtain competitive results on several unsupervised MT benchmarks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

42 of 59 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  6. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  7. 2018Deep contextualized word representationscited by 2,290
  8. 2016Density estimation using Real NVPcited by 2,042
  9. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  11. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  12. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
30 more
  1. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  2. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  3. 2017Word Translation Without Parallel Datacited by 487
  4. 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 347
  5. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  6. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  7. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  8. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  9. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 215
  10. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  11. 2017Unsupervised Neural Machine Translationcited by 149
  12. 2016Modeling Coverage for Neural Machine Translationcited by 110
  13. 2019FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flowcited by 89
  14. 2020On the Sentence Embeddings from Pre-trained Language Modelscited by 83
  15. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
  16. 2017Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Descriptioncited by 76
  17. 2019Discrete Flows: Invertible Generative Models of Discrete Datacited by 68
  18. 2019Latent Normalizing Flows for Discrete Sequencescited by 67
  19. 2019Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posteriorcited by 58
  20. 2020Code-switching pre-training for neural machine translationcited by 43
  21. 2020A Call for More Rigor in Unsupervised Cross-lingual Learningcited by 37
  22. 2016Semi-Supervised Learning for Neural Machine Translationcited by 36
  23. 2016Variational Neural Machine Translationcited by 35
  24. 2019AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flowscited by 33
  25. 2021Multilingual Unsupervised Neural Machine Translation with Denoising Adapterscited by 22
  26. 2019Universal audio synthesizer control with normalizing flowscited by 17
  27. 2018Unsupervised Neural Machine Translation with Weight Sharingcited by 15
  28. 2018Auto-Encoding Variational Neural Machine Translationcited by 11
  29. 2020Variational Neural Machine Translation with Normalizing Flowscited by 7
  30. 2020Latent Transformations for Discrete-Data Normalising Flowscited by 1

Built on by

Cited by year

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

4 papers.

  1. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4
  2. 2024LangSAMP: Language-Script Aware Multilingual Pretrainingcited by 2
  3. 2023On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Losscited by 1
  4. 2023An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contributioncited by 0