Can neural machine translation do simultaneous translation?
Not on the map. Why?
Abstract (arXiv)
We investigate the potential of attention-based neural machine translation in simultaneous translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding, that allows an existing neural machine translation model to begin translating before a full source sentence is received. This approach is unique from previous works on simultaneous translation in that segmentation and translation are done jointly to maximize the translation quality and that translating each segment is strongly conditioned on all the previous segments. This paper presents a first step toward building a full simultaneous translation system based on neural machine translation.
Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jun 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 21; 2022: 14; 2023: 20; 2024: 13; 2025: 11; 2026: 7.
86 papers.
Sort:
By area:
- 2022Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translationcited by 57
- 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
- 2021Learning When to Translate for Streaming Speechcited by 30
- 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
- 2021SimulSLT: End-to-End Simultaneous Sign Language Translationcited by 27
- 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
38 more
- 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
- 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited 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
- 2022Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translationcited by 14
- 2024Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agentcited by 14
- 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
- 2021Stream-level Latency Evaluation for Simultaneous Machine Translationcited by 12
- 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
- 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
- 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
- 2022MT Metrics Correlate with Human Ratings of Simultaneous Speech Translationcited by 9
- 2023Simultaneous Machine Translation with Large Language Modelscited by 9
- 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voicecited by 9
- 2021Towards the evaluation of automatic simultaneous speech translation from a communicative perspectivecited by 8
- 2023Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoffcited by 8
- 2023Efficient Monotonic Multihead Attentioncited by 8
- 2021Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translationcited by 7
- 2021It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Datacited by 7
- 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translationcited by 7
- 2021Simultaneous Multi-Pivot Neural Machine Translationcited by 6
- 2023Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inferencecited by 6
- 2023Long-Form End-to-End Speech Translation via Latent Alignment Segmentationcited by 6
- 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
- 2024Direct Speech-to-Speech Neural Machine Translation: A Surveycited by 6
- 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
- 2024Self-Modifying State Modeling for Simultaneous Machine Translationcited by 5
- 2021Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translationcited by 4
- 2021Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinementcited by 4
- 2023Efficient Encoders for Streaming Sequence Taggingcited by 4
- 2023LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translationcited by 4
- 2024Overcoming Non-monotonicity in Transducer-based Streaming Generationcited by 4
- 2025Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translationcited by 4
50 most cited of 86 All 86 (JSON)
- 2026Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation2 Oct 2026
- 2026Simultaneous Translation between Sign Languages28 Sep 2026
- 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation24 Sep 2026
- 2026TRADE: Transducer-Augmented Decoder for Speech LLM7 Jun 2026
- 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignment12 Mar 2026
- 2026Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches3 Mar 2026
- 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies16 Jan 2026
- 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies26 Sep 2025
- 2025Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation22 Sep 2025
- 2025Direct Simultaneous Translation Activation for Large Audio-Language Models19 Sep 2025
- 2025Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization19 Sep 2025
- 2025Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT18 Aug 2025
38 more
- 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice23 Jul 2025
- 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation27 May 2025
- 2025Spatial Speech Translation: Translating Across Space With Binaural Hearables25 Apr 2025
- 2025Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation28 Mar 2025
- 2025Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation14 Mar 2025
- 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translation2 Feb 2025
- 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?24 Dec 2024
- 2024Overcoming Non-monotonicity in Transducer-based Streaming Generation26 Nov 2024
- 2024Direct Speech-to-Speech Neural Machine Translation: A Survey13 Nov 2024
- 2024CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation21 Oct 2024
- 2024What does it take to get state of the art in simultaneous speech-to-speech translation?2 Sep 2024
- 2024Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent31 Jul 2024
- 2024Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters18 Jul 2024
- 2024NAIST Simultaneous Speech Translation System for IWSLT 202430 Jun 2024
- 2024A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation11 Jun 2024
- 2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning5 Jun 2024
- 2024Self-Modifying State Modeling for Simultaneous Machine Translation4 Jun 2024
- 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation16 May 2024
- 2024TransLLaMa: LLM-based Simultaneous Translation System7 Feb 2024
- 2023Language Model is a Branch Predictor for Simultaneous Machine Translation22 Dec 2023
- 2023Efficient Monotonic Multihead Attention7 Dec 2023
- 2023Average Token Delay: A Duration-aware Latency Metric for Simultaneous Translation24 Nov 2023
- 2023Context Consistency between Training and Testing in Simultaneous Machine Translation13 Nov 2023
- 2023Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing27 Oct 2023
- 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generation27 Oct 2023
- 2023Enhanced Simultaneous Machine Translation with Word-level Policies25 Oct 2023
- 2023Non-autoregressive Streaming Transformer for Simultaneous Translation23 Oct 2023
- 2023Long-form Simultaneous Speech Translation: Thesis Proposal17 Oct 2023
- 2023Segmentation-Free Streaming Machine Translation26 Sep 2023
- 2023Long-Form End-to-End Speech Translation via Latent Alignment Segmentation20 Sep 2023
- 2023Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff20 Sep 2023
- 2023Simultaneous Machine Translation with Large Language Models13 Sep 2023
- 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentation25 May 2023
- 2023Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks4 May 2023
- 2023LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation21 Mar 2023
- 2023Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference14 Mar 2023
- 2023Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation2 Mar 2023
- 2023Hidden Markov Transformer for Simultaneous Machine Translation1 Mar 2023
50 newest of 86 All 86 (JSON)
- 2022Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translationcited by 57
- 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
- 2021Learning When to Translate for Streaming Speechcited by 30
- 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
- 2021SimulSLT: End-to-End Simultaneous Sign Language Translationcited by 27
- 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
12 most cited of 81 All 81 (JSON)
- 2026Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation2 Oct 2026
- 2026Simultaneous Translation between Sign Languages28 Sep 2026
- 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation24 Sep 2026
- 2026TRADE: Transducer-Augmented Decoder for Speech LLM7 Jun 2026
- 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignment12 Mar 2026
- 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies16 Jan 2026
- 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies26 Sep 2025
- 2025Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation22 Sep 2025
- 2025Direct Simultaneous Translation Activation for Large Audio-Language Models19 Sep 2025
- 2025Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization19 Sep 2025
- 2025Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT18 Aug 2025
- 2025Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice23 Jul 2025
12 newest of 81 All 81 (JSON)