Opportunistic Decoding with Timely Correction for Simultaneous Translation
Not on the map. Why?
Abstract (arXiv)
Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and latency, i.e., the decoding policy is usually either too aggressive or too conservative. We propose an opportunistic decoding technique with timely correction ability, which always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information. At the same time, it also corrects, in a timely fashion, the mistakes in the former overgenerated words when observing more source context to ensure high translation quality. Experiments show our technique achieves substantial reduction in latency and up to +3.1 increase in BLEU, with revision rate under 8% in Chinese-to-English and English-to-Chinese translation.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 0; 2023: 3; 2024: 1.
8 papers.
- 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
- 2021Learning When to Translate for Streaming Speechcited by 30
- 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
- 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
- 2021Simultaneous Multi-Pivot Neural Machine Translationcited by 6
- 2023TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Modelcited by 5
- 2021Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinementcited by 4
- 2023The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labellingcited by 2
- 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?24 Dec 2024
- 2023The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labelling28 Jul 2023
- 2023TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model18 May 2023
- 2023Hidden Markov Transformer for Simultaneous Machine Translation1 Mar 2023
- 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics16 Dec 2021
- 2021Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement18 Oct 2021
- 2021Learning When to Translate for Streaming Speech15 Sep 2021
- 2021Simultaneous Multi-Pivot Neural Machine Translation15 Apr 2021