Data to 14 Oct 2026

Monotonic Infinite Lookback Attention for Simultaneous Machine Translation

arXiv 1906.05218 ↗First posted 12 Jun 2019cs.CLcited by 104

Not on the map. Why?

Abstract (arXiv)

Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simultaneous systems must carefully schedule their reading of the source sentence to balance quality against latency. We present the first simultaneous translation system to learn an adaptive schedule jointly with a neural machine translation (NMT) model that attends over all source tokens read thus far. We do so by introducing Monotonic Infinite Lookback (MILk) attention, which maintains both a hard, monotonic attention head to schedule the reading of the source sentence, and a soft attention head that extends from the monotonic head back to the beginning of the source. We show that MILk's adaptive schedule allows it to arrive at latency-quality trade-offs that are favorable to those of a recently proposed wait-k strategy for many latency values.

Key facts. Cited by 104 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 23; 2022: 20; 2023: 21; 2024: 17; 2025: 12; 2026: 10.

104 papers.

Sort:

By area:

2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
2023End-to-End Speech Recognition: A Surveycited by 129
2021Translating Images into Mapscited by 115
2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 40
2022Information-Transport-based Policy for Simultaneous Translationcited by 40
2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
2022Attention as a Guide for Simultaneous Speech Translationcited by 32
2021Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASRcited by 31
2022Large-Scale Streaming End-to-End Speech Translation with Neural Transducerscited by 31
2021Learning When to Translate for Streaming Speechcited by 30
2021SimulSLT: End-to-End Simultaneous Sign Language Translationcited by 27

38 more

2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 25
2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learningcited by 21
2023Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Taskscited by 20
2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
2021BSTC: A Large-Scale Chinese-English Speech Translation Datasetcited by 16
2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
2022Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translationcited by 16
2022Average Token Delay: A Latency Metric for Simultaneous Translationcited by 15
2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
2024Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Timecited by 15
2021An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategiescited by 14
2021Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognitioncited by 14
2022Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translationcited by 14
2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
2025Chronological Thinking in Full-Duplex Spoken Dialogue Language Modelscited by 14
2021The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021cited by 13
2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
2022A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capabilitycited by 12
2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learningcited by 10
2024A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translationcited by 10
2021Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attentioncited by 9
2022From Simultaneous to Streaming Machine Translation by Leveraging Streaming Historycited by 9
2023Simultaneous Machine Translation with Large Language Modelscited by 9
2023Adaptive Policy with Wait-k Model for Simultaneous Translationcited by 9
2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voicecited by 9
2021Simultaneous Speech Translation for Live Subtitling: from Delay to Displaycited by 8
2023Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoffcited by 8
2023Efficient Monotonic Multihead Attentioncited by 8
2024Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detectioncited by 7
2021Decision Attentive Regularization to Improve Simultaneous Speech Translation Systemscited by 6
2022Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translationcited by 6
2023Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inferencecited by 6
2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
2023Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Modelscited by 6

50 most cited of 104 All 104 (JSON)