mlsanityData to 7 Oct 2026

Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning

arXiv 2002.04306 ↗First posted 11 Feb 2020cs.CL cs.AI cs.LGcited by 10

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

We present a novel approach to efficiently learn a simultaneous translation model with coupled programmer-interpreter policies. First, wepresent an algorithmic oracle to produce oracle READ/WRITE actions for training bilingual sentence-pairs using the notion of word alignments. This oracle actions are designed to capture enough information from the partial input before writing the output. Next, we perform a coupled scheduled sampling to effectively mitigate the exposure bias when learning both policies jointly with imitation learning. Experiments on six language-pairs show our method outperforms strong baselines in terms of translation quality while keeping the translation delay low.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 36 references that are in the map. First posted on arXiv 11 Feb 2020.

Builds on

19 of 36 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  7. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  8. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  9. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  10. 2019Direct speech-to-speech translation with a sequence-to-sequence modelcited by 118
  11. 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 103
  12. 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
7 more
  1. 2019Recent Advances in Imitation Learning from Observationcited by 92
  2. 2018Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translationcited by 51
  3. 2019Simpler and Faster Learning of Adaptive Policies for Simultaneous Translationcited by 36
  4. 2018Low-Latency Neural Speech Translationcited by 35
  5. 2019Thinking Slow about Latency Evaluation for Simultaneous Machine Translationcited by 28
  6. 2019Simultaneous Translation with Flexible Policy via Restricted Imitation Learningcited by 22
  7. 2019Parallel Scheduled Samplingcited by 17

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 1; 2025: 1.

10 papers.

  1. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
  2. 2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
  3. 2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
  4. 2023Simultaneous Machine Translation with Large Language Modelscited by 9
  5. 2021Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translationcited by 7
  6. 2021It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Datacited by 7
  7. 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
  8. 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Modelscited by 4
  9. 2022Supervised Visual Attention for Simultaneous Multimodal Machine Translationcited by 2
  10. 2023NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpuscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation
  2. 2020Learning to Multi-Task Learn for Better Neural Machine Translation
  3. 2025RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
  4. 2026Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
  5. 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translation
  6. 2026PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning
  7. 2021Fixing exposure bias with imitation learning needs powerful oracles
  8. 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation