mlsanityData to 7 Oct 2026

Learning to Translate in Real-time with Neural Machine Translation

arXiv 1610.00388 ↗First posted 3 Oct 2016cs.CL cs.LGcited by 97

Not on the map. Why?

Abstract (arXiv)

Translating in real-time, a.k.a. simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 21; 2022: 16; 2023: 22; 2024: 19; 2025: 11; 2026: 7.

97 papers.

Sort:

By area:

  1. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  2. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 137
  3. 2022Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translationcited by 56
  4. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  5. 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 39
  6. 2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
  7. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  8. 2021Survey on reinforcement learning for language processingcited by 31
  9. 2021Learning When to Translate for Streaming Speechcited by 30
  10. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
  11. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  12. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
38 more
  1. 2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learningcited by 20
  2. 2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
  3. 2021BSTC: A Large-Scale Chinese-English Speech Translation Datasetcited by 16
  4. 2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
  5. 2022Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translationcited by 16
  6. 2022Average Token Delay: A Latency Metric for Simultaneous Translationcited by 15
  7. 2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
  8. 2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
  9. 2024Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agentcited by 14
  10. 2021The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021cited by 13
  11. 2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
  12. 2024SiLLM: Large Language Models for Simultaneous Machine Translationcited by 13
  13. 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
  14. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  15. 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
  16. 2024Decoder-only Streaming Transformer for Simultaneous Translationcited by 11
  17. 2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learningcited by 10
  18. 2023Glancing Future for Simultaneous Machine Translationcited by 10
  19. 2024A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translationcited by 10
  20. 2021Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attentioncited by 9
  21. 2023Simultaneous Machine Translation with Large Language Modelscited by 9
  22. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  23. 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voicecited by 9
  24. 2021Towards the evaluation of automatic simultaneous speech translation from a communicative perspectivecited by 8
  25. 2021Simultaneous Speech Translation for Live Subtitling: from Delay to Displaycited by 8
  26. 2023Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoffcited by 8
  27. 2023Adaptive Policy with Wait-k Model for Simultaneous Translationcited by 8
  28. 2023Efficient Monotonic Multihead Attentioncited by 8
  29. 2021Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translationcited by 7
  30. 2021SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memorycited by 7
  31. 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translationcited by 7
  32. 2021Simultaneous Multi-Pivot Neural Machine Translationcited by 6
  33. 2022Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translationcited by 6
  34. 2023Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Datacited by 6
  35. 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
  36. 2023Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Modelscited by 6
  37. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  38. 2023TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Modelcited by 5

50 most cited of 97 All 97 (JSON)