mlsanityData to 14 Oct 2026

Modeling Dual Read/Write Paths for Simultaneous Machine Translation

arXiv 2203.09163 ↗First posted 17 Mar 2022cs.CL cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

Simultaneous machine translation (SiMT) outputs translation while reading source sentence and hence requires a policy to decide whether to wait for the next source word (READ) or generate a target word (WRITE), the actions of which form a read/write path. Although the read/write path is essential to SiMT performance, no direct supervision is given to the path in the existing methods. In this paper, we propose a method of dual-path SiMT which introduces duality constraints to direct the read/write path. According to duality constraints, the read/write path in source-to-target and target-to-source SiMT models can be mapped to each other. As a result, the two SiMT models can be optimized jointly by forcing their read/write paths to satisfy the mapping. Experiments on En-Vi and De-En tasks show that our method can outperform strong baselines under all latency.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

23 of 38 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  4. 2016Dual Learning for Machine Translationcited by 148
  5. 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 104
  6. 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
  7. 2019Monotonic Multihead Attentioncited by 93
  8. 2016Can neural machine translation do simultaneous translation?cited by 86
  9. 2017Online and Linear-Time Attention by Enforcing Monotonic Alignmentscited by 85
  10. 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 61
  11. 2018Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translationcited by 52
  12. 2019An Effective Approach to Unsupervised Machine Translationcited by 37
11 more
  1. 2019Simpler and Faster Learning of Adaptive Policies for Simultaneous Translationcited by 37
  2. 2017Dual Supervised Learningcited by 33
  3. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  4. 2016Neural Machine Translation with Supervised Attentioncited by 31
  5. 2017What does Attention in Neural Machine Translation Pay Attention to?cited by 30
  6. 2020Future-Guided Incremental Transformer for Simultaneous Translationcited by 30
  7. 2019Simultaneous Translation with Flexible Policy via Restricted Imitation Learningcited by 22
  8. 2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learningcited by 10
  9. 2020Neural Simultaneous Speech Translation Using Alignment-Based Chunkingcited by 8
  10. 2018Zero-Shot Dual Machine Translationcited by 6
  11. 2021Infusing Future Information into Monotonic Attention Through Language Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 12; 2024: 6.

21 papers.

Sort:

By area:

  1. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  2. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 25
  3. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  4. 2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learningcited by 21
  5. 2022Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translationcited by 16
  6. 2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
  7. 2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
  8. 2024Decoder-only Streaming Transformer for Simultaneous Translationcited by 11
  9. 2023Glancing Future for Simultaneous Machine Translationcited by 10
  10. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  11. 2023Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inferencecited by 6
  12. 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
9 more
  1. 2024Self-Modifying State Modeling for Simultaneous Machine Translationcited by 5
  2. 2023LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translationcited by 4
  3. 2023Enhanced Simultaneous Machine Translation with Word-level Policiescited by 2
  4. 2023Language Model is a Branch Predictor for Simultaneous Machine Translationcited by 2
  5. 2024Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Modelscited by 2
  6. 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
  7. 2024R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translationcited by 1
  8. 2024On the Hallucination in Simultaneous Machine Translationcited by 1
  9. 2023Context Consistency between Training and Testing in Simultaneous Machine Translationcited by 0