mlsanityData to 14 Oct 2026

Facebook FAIR's WMT19 News Translation Task Submission

arXiv 1907.06616 ↗First posted 15 Jul 2019cs.CLcited by 179

Not on the map. Why?

Abstract (arXiv)

This paper describes Facebook FAIR's submission to the WMT19 shared news translation task. We participate in two language pairs and four language directions, English <-> German and English <-> Russian. Following our submission from last year, our baseline systems are large BPE-based transformer models trained with the Fairseq sequence modeling toolkit which rely on sampled back-translations. This year we experiment with different bitext data filtering schemes, as well as with adding filtered back-translated data. We also ensemble and fine-tune our models on domain-specific data, then decode using noisy channel model reranking. Our submissions are ranked first in all four directions of the human evaluation campaign. On En->De, our system significantly outperforms other systems as well as human translations. This system improves upon our WMT'18 submission by 4.5 BLEU points.

Key facts. Cited by 179 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 53; 2022: 46; 2023: 41; 2024: 30; 2025: 6; 2026: 3.

179 papers.

Sort:

By area:

  1. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  2. 2022In-context Examples Selection for Machine Translationcited by 172
  3. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  4. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  5. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 130
  6. 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 120
  7. 2022Locally Typical Samplingcited by 111
  8. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  9. 2021Efficient Nearest Neighbor Language Modelscited by 93
  10. 2022On Decoding Strategies for Neural Text Generatorscited by 90
  11. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  12. 2021Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasurescited by 73
38 more
  1. 2022Do Language Models Plagiarize?cited by 73
  2. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  3. 2021Adaptive Nearest Neighbor Machine Translationcited by 58
  4. 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
  5. 2022On the Limitations of Reference-Free Evaluations of Generated Textcited by 52
  6. 2022Quality-Aware Decoding for Neural Machine Translationcited by 49
  7. 2021Differentiable Subset Pruning of Transformer Headscited by 47
  8. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  9. 2022Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionalitycited by 44
  10. 2021Generate, Annotate, and Learn: NLP with Synthetic Textcited by 42
  11. 2022Things not Written in Text: Exploring Spatial Commonsense from Visual Signalscited by 41
  12. 2022Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspectivecited by 41
  13. 2023GPT-who: An Information Density-based Machine-Generated Text Detectorcited by 40
  14. 2022A Survey on Cross-Lingual Summarizationcited by 38
  15. 2023Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websitescited by 38
  16. 2021Fast Nearest Neighbor Machine Translationcited by 37
  17. 2021SHAPE: Shifted Absolute Position Embedding for Transformerscited by 37
  18. 2023ConDA: Contrastive Domain Adaptation for AI-generated Text Detectioncited by 37
  19. 2022Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Followingcited by 33
  20. 2021Bidimensional Leaderboards: Generate and Evaluate Language Hand in Handcited by 32
  21. 2021fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkitcited by 24
  22. 2022Efficient Cluster-Based k-Nearest-Neighbor Machine Translationcited by 24
  23. 2024Benchmarking Large Multimodal Models against Common Corruptionscited by 24
  24. 2022ALLSH: Active Learning Guided by Local Sensitivity and Hardnesscited by 23
  25. 2021Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoningcited by 21
  26. 2022Chunk-based Nearest Neighbor Machine Translationcited by 21
  27. 2022CoNT: Contrastive Neural Text Generationcited by 21
  28. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  29. 2023Augmenting Large Language Model Translators via Translation Memoriescited by 21
  30. 2024Linear-time Minimum Bayes Risk Decoding with Reference Aggregationcited by 21
  31. 2024Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddingscited by 21
  32. 2021Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translationcited by 20
  33. 2021Cross-lingual Visual Pre-training for Multimodal Machine Translationcited by 19
  34. 2023Aligning Neural Machine Translation Models: Human Feedback in Training and Inferencecited by 19
  35. 2021Determinantal Beam Searchcited by 18
  36. 2021Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translationcited by 17
  37. 2022LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Modelscited by 16
  38. 2023Adaptive Gating in Mixture-of-Experts based Language Modelscited by 16

50 most cited of 179 All 179 (JSON)