Lune

EMNLP Findings2023

Enhanced Simultaneous Machine Translation with Word-level Policies

Kang Kim, Hankyu Cho

Abstract

Recent years have seen remarkable advances in the field of Simultaneous Machine Translation (SiMT) due to the introduction of innovative policies that dictate whether to READ or WRITE at each step of the translation process. However, a common assumption in many existing studies is that operations are carried out at the subword level, even though the standard unit for input and output in most practical scenarios is typically at the word level. This paper demonstrates that policies devised and validated at the subword level are surpassed by those operating at the word level, which process multiple subwords to form a complete word in a single step. Additionally, we suggest a method to boost SiMT models using language models (LMs), wherein the proposed word-level policy plays a vital role in addressing the subword disparity between LMs and SiMT models. Code is available at https://github.com/xl8-ai/WordSiMT.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Incorporating BERT into Neural Machine Translation cites Towards Making the Most of BERT in Neural Machine Translation
  • PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation cites Monotonic Multihead Attention
  • Few-shot Learning with Multilingual Generative Language Models cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine TranslationLibo Zhao, Jing Li, Ziqian ZengEMNLP 2024 · 1 citation
  2. Self-Modifying State Modeling for Simultaneous Machine TranslationDonglei Yu, Xiaomian Kang, Yuchen Liu, Yu Zhou et al.ACL 2024

Builds on23

  1. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  2. Incorporating BERT into Neural Machine TranslationJinhua Zhu, Yingce Xia, Lijun Wu, Di He et al.ICLR 2020 · 391 citations
  3. Towards Making the Most of BERT in Neural Machine TranslationJiacheng Yang, Mingxuan Wang, Hao Zhou, Chengqi Zhao et al.AAAI 2020 · 164 citations
  4. Monotonic Multihead AttentionXutai Ma, Juan Miguel Pino, James Cross, Liezl Puzon et al.ICLR 2020 · 148 citations
  5. Few-shot Learning with Multilingual Generative Language ModelsXi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang et al.EMNLP 2022 · 113 citations

Related papers

  1. Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine TranslationShaolei Zhang, Shoutao Guo, Yang FengEMNLP Findings 2022 · 13 citations
  2. Modeling Dual Read/Write Paths for Simultaneous Machine TranslationShaolei Zhang, Yang FengACL 2022 · 27 citations
  3. Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k PolicyShaolei Zhang, Yang FengEMNLP 2021 · 19 citations
  4. SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine TranslationTing Xu, Zhichao Huang, Jiankai Sun, Shanbo Cheng et al.ACL Findings 2025 · 1 citation
  5. Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language ModelsVictor Agostinelli, Max Wild, Matthew Raffel, Kazi Ahmed Asif Fuad et al.ACL 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines