mlsanityData to 7 Oct 2026

Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings

arXiv 2010.11247 ↗First posted 21 Oct 2020cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the lack of large-scale, high-quality simultaneous translation datasets, most such systems are still trained on conventional full-sentence bitexts. This is far from ideal for the simultaneous scenario due to the abundance of unnecessary long-distance reorderings in those bitexts. We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh->En and Ja->En simultaneous translation show substantial improvements (up to +2.7 BLEU) with the addition of these generated pseudo-references.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 6; 2025: 2; 2026: 2.

20 papers.

Sort:

By area:

  1. 2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
  2. 2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
  3. 2024SiLLM: Large Language Models for Simultaneous Machine Translationcited by 13
  4. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  5. 2024Decoder-only Streaming Transformer for Simultaneous Translationcited by 11
  6. 2023Glancing Future for Simultaneous Machine Translationcited by 10
  7. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  8. 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translationcited by 7
  9. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  10. 2022PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Populationcited by 5
  11. 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
  12. 2024Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Paircited by 3
8 more
  1. 2023Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approachcited by 2
  2. 2024Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Modelscited by 2
  3. 2024PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translationcited by 2
  4. 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
  5. 2024On the Hallucination in Simultaneous Machine Translationcited by 1
  6. 2023Rethinking the Reasonability of the Test Set for Simultaneous Machine Translationcited by 0
  7. 2026Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approachcited by 0
  8. 2026Dual-Stream Simultaneous Translation via 2D Grid Attentioncited by 0