通过注意力对齐学习读写策略，实现低延迟高精度的同步翻译。
Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation
- 基于源目标词对齐构建读写决策边界，控制翻译进度。
- 在多个数据集上超越现有基线，接近非流式模型性能。
- 小规模分类模块可灵活调节延迟与质量平衡，适合实时场景。
同步机器翻译在接收输入流的同时生成译文，面临译文质量与延迟之间的权衡。本文提出一种高效方法：利用预训练非流式模型（具序列到序列机制）的源目标词对齐信息，将其转化为流式模型。通过该对齐关系学习读写决策边界，以最小输入量实现可靠译文生成。训练时，采用监督学习在对齐点（伪标签）上优化读写策略模块。该模块为小型二分类单元，可在推理阶段灵活调控质量与延迟。实验表明，所提模型优于多个强基线，并显著缩小了与非流式基准模型的差距。
原文摘要 · Abstract (English)
Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal latency. We propose an approach that efficiently manages this trade-off. By enhancing a pretrained non-streaming model, which was trained with a seq2seq mechanism and represents the upper bound in quality, we convert it into a streaming model by utilizing the alignment between source and target tokens. This alignment is used to learn a read/write decision boundary for reliable translation generation with minimal input. During training, the model learns the decision boundary through a read/write policy module, employing supervised learning on the alignment points (pseudo labels). The read/write policy module, a small binary classification unit, can control the quality/latency trade-off during inference. Experimental results show that our model outperforms several strong baselines and narrows the gap with the non-streaming baseline model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。