mlsanityData to 14 Oct 2026

WeChat Neural Machine Translation Systems for WMT21

arXiv 2108.02401 ↗First posted 5 Aug 2021cs.CL cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) with several novel and effective variants. In our experiments, we employ data filtering, large-scale synthetic data generation (i.e., back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge transfer), advanced finetuning approaches, and boosted Self-BLEU based model ensemble. Our constrained systems achieve 36.9, 46.9, 27.8 and 31.3 case-sensitive BLEU scores on English->Chinese, English->Japanese, Japanese->English and English->German, respectively. The BLEU scores of English->Chinese, English->Japanese and Japanese->English are the highest among all submissions, and that of English->German is the highest among all constrained submissions.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 5 Aug 2021.

Builds on

21 of 29 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2020On Layer Normalization in the Transformer Architecturecited by 922
  4. 2016Sequence-Level Knowledge Distillationcited by 801
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  6. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  7. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  8. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  9. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  10. 2019Tagged Back-Translationcited by 77
  11. 2020Talking-Heads Attentioncited by 62
  12. 2020On the Inference Calibration of Neural Machine Translationcited by 61
9 more
  1. 2020Very Deep Transformers for Neural Machine Translationcited by 50
  2. 2019Scheduled Sampling for Transformerscited by 48
  3. 2021Selective Knowledge Distillation for Neural Machine Translationcited by 43
  4. 2018Accelerating Neural Transformer via an Average Attention Networkcited by 22
  5. 2019Parallel Scheduled Samplingcited by 17
  6. 2018DTMT: A Novel Deep Transition Architecture for Neural Machine Translationcited by 13
  7. 2020Multi-Unit Transformers for Neural Machine Translationcited by 13
  8. 2020WeChat Neural Machine Translation Systems for WMT20cited by 11
  9. 2021Confidence-Aware Scheduled Sampling for Neural Machine Translationcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 5; 2024: 1.

11 papers.

  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  2. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 145
  3. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  4. 2024Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languagescited by 36
  5. 2021Scheduled Sampling Based on Decoding Steps for Neural Machine Translationcited by 11
  6. 2023Instruction Position Matters in Sequence Generation with Large Language Modelscited by 10
  7. 2022DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decodingcited by 4
  8. 2023SOTASTREAM: A Streaming Approach to Machine Translation Trainingcited by 3
  9. 2022BJTU-WeChat's Systems for the WMT22 Chat Translation Taskcited by 1
  10. 2022Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Taskcited by 0
  11. 2023Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Facebook AI WMT21 News Translation Task Submission
  2. 2021The NiuTrans Machine Translation Systems for WMT21
  3. 2024Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Task
  4. 2021NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21
  5. 2023Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
  6. 2021The USYD-JD Speech Translation System for IWSLT 2021
  7. 2022The RoyalFlush System for the WMT 2022 Efficiency Task
  8. 2022Improving Simultaneous Machine Translation with Monolingual Data