mlsanityData to 7 Oct 2026

Efficient Wait-k Models for Simultaneous Machine Translation

arXiv 2005.08595 ↗First posted 18 May 2020cs.CL cs.SD eess.AScited by 59

Not on the map. Why?

Abstract (arXiv)

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 14; 2024: 13; 2025: 7; 2026: 6.

59 papers.

Sort:

By area:

  1. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  2. 2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
  3. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  4. 2021Learning When to Translate for Streaming Speechcited by 30
  5. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
  6. 2022Does Simultaneous Speech Translation need Simultaneous Models?cited by 22
  7. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  8. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
  9. 2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learningcited by 20
  10. 2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
  11. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  12. 2022Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translationcited by 16
38 more
  1. 2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
  2. 2021An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategiescited by 14
  3. 2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
  4. 2024SiLLM: Large Language Models for Simultaneous Machine Translationcited by 13
  5. 2021Stream-level Latency Evaluation for Simultaneous Machine Translationcited by 12
  6. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  7. 2024Decoder-only Streaming Transformer for Simultaneous Translationcited by 11
  8. 2022From Simultaneous to Streaming Machine Translation by Leveraging Streaming Historycited by 9
  9. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  10. 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voicecited by 9
  11. 2021Simultaneous Speech Translation for Live Subtitling: from Delay to Displaycited by 8
  12. 2023Adaptive Policy with Wait-k Model for Simultaneous Translationcited by 8
  13. 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translationcited by 7
  14. 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
  15. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  16. 2024Self-Modifying State Modeling for Simultaneous Machine Translationcited by 5
  17. 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
  18. 2021Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translationcited by 4
  19. 2025Large Language Models Are Read/Write Policy-Makers for Simultaneous Generationcited by 4
  20. 2021The Volctrans Neural Speech Translation System for IWSLT 2021cited by 3
  21. 2024Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Paircited by 3
  22. 2025Spatial Speech Translation: Translating Across Space With Binaural Hearablescited by 3
  23. 2021One Source, Two Targets: Challenges and Rewards of Dual Decodingcited by 2
  24. 2021Visualization: the missing factor in Simultaneous Speech Translationcited by 2
  25. 2022Supervised Visual Attention for Simultaneous Multimodal Machine Translationcited by 2
  26. 2023NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpuscited by 2
  27. 2023Segmentation-Free Streaming Machine Translationcited by 2
  28. 2023Enhanced Simultaneous Machine Translation with Word-level Policiescited by 2
  29. 2023Language Model is a Branch Predictor for Simultaneous Machine Translationcited by 2
  30. 2024Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Modelscited by 2
  31. 2024Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapterscited by 2
  32. 2024PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translationcited by 2
  33. 2026Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputscited by 2
  34. 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
  35. 2024On the Hallucination in Simultaneous Machine Translationcited by 1
  36. 2024What does it take to get state of the art in simultaneous speech-to-speech translation?cited by 1
  37. 2024Anticipating Future with Large Language Model for Simultaneous Machine Translationcited by 1
  38. 2021Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategycited by 0

50 most cited of 59 All 59 (JSON)