mlsanityData to 7 Oct 2026

The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21

arXiv 2109.11247 ↗First posted 23 Sep 2021cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables fast and accurate parallel decoding in contrast to the currently prevailing autoregressive models. To the best of our knowledge, this is the first parallel translation system that can be scaled to such a practical scenario like WMT competition. More importantly, our parallel translation system achieves the best BLEU score (35.0) on German->English translation task, outperforming all strong autoregressive counterparts.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 23 Sep 2021.

Builds on

15 of 22 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  6. 2016Sequence-Level Knowledge Distillationcited by 761
  7. 2017Non-Autoregressive Neural Machine Translationcited by 457
  8. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  9. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  10. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
  11. 2020Vocabulary Learning via Optimal Transport for Neural Machine Translationcited by 58
  12. 2019Domain, Translationese and Noise in Synthetic Data for Neural Machine Translationcited by 26
3 more
  1. 2018Joint Training for Neural Machine Translation Models with Monolingual Datacited by 20
  2. 2020WeChat Neural Machine Translation Systems for WMT20cited by 11
  3. 2020The Volctrans Machine Translation System for WMT20cited by 7

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 9.

14 papers.

Sort:

By area:

  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  2. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  3. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  4. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  5. 2023Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuningcited by 39
  6. 2022On the Learning of Non-Autoregressive Transformerscited by 27
  7. 2022textitlatent-GLAT: Glancing at Latent Variables for Parallel Text Generationcited by 20
  8. 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translationcited by 11
  9. 2023INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translationcited by 6
  10. 2022On the Effectiveness of Automated Metrics for Text Generation Systemscited by 4
  11. 2023Accurate Knowledge Distillation with n-best Rerankingcited by 4
  12. 2022PARAGEN : A Parallel Generation Toolkitcited by 2
2 more
  1. 2023Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translationcited by 2
  2. 2023Attentive Multi-Layer Perceptron for Non-autoregressive Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Accelerating Transformer Inference for Translation via Parallel Decoding
  2. 2022Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators
  3. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
  4. 2024Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
  5. 2024Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
  6. 2024Analysis of Levenshtein Transformer's Decoder and Its Variants
  7. 2023Samsung R&D Institute Philippines at WMT 2023
  8. 2026Efficient One-to-Many Translation with Joint Multi-Stream Diffusion