同传译者启发下的实时人工智能翻译新方法：实时机器翻译（SiMT）旨在提供源语言的即时翻译，包括口语和书面语的翻译。传统的方法需要模型来控制何时“读取”更多源语言，何时“产出”译文——这些决策依赖于大量的模型训练、复杂的模型设计和强大的计算能力。香港理工大学和华南理工大学的研究人员赵立波、李菁和曾子倩推出了PsFuture，这是一种零样本、可调整的读写策略，能让实时机器翻译模型无需额外训练即可提供实时翻译。PsFuture可让翻译模
实时机器翻译（SiMT）旨在提供源语言的即时翻译，包括口语和书面语的翻译。
Traditionally, this requires models that control when to “read” more of the source and when to “write” the translation — decisions that rely on intensive model training, complex model designs, and significant computing power.
传统的方法需要模型来控制何时“读取”更多源语言，何时“产出”译文——这些决策依赖于大量的模型训练、复杂的模型设计和强大的计算能力。
Now, researchers Libo Zhao, Jing Li, and Ziqian Zeng from Hong Kong Polytechnic University and South China University of Technology have introduced PsFuture, a zero-shot, adaptable read/write policy that enables SiMT models to make real-time translation decisions without additional training.
如今，香港理工大学和华南理工大学的研究人员赵立波、李菁和曾子倩推出了PsFuture，这是一种零样本、可调整的读写策略，能让实时机器翻译模型无需额外训练即可提供实时翻译。
The researchers said they drew inspiration from human interpreters, who dynamically decide when to listen and when to speak based on evolving contexts.
研究人员指出，他们从人类口译员身上汲取了灵感，人类口译员会根据不断变化的语境，灵活决定何时该听，何时该说。
“Interpreters shift from listening to translating upon anticipating that further future words would not impact their current decisions,” they explained.
研究人员解释道：“如果口译员预计后面要说的话不会影响当下所做的决定，就会由听转为译。”
PsFuture allows translation models to make similar, context-aware decisions, leveraging “the model’s inherent linguistic comprehension and translation proficiency” and eliminating the need for further training.
PsFuture可让翻译模型做出类似的决策并理解上下文，利用“模型自身的语言理解和翻译能力”，无需额外训练。
Simulated Look-Ahead
模拟预测能力
Rather than relying on a fixed number of source words to determine the right time to start translating, PsFuture allows a model to anticipate what’s coming next. PsFuture不依靠固定数量的源语言词汇来确定开始翻译的恰当时机，而是让模型预测接下来的内容。
By using pseudo-future information — a simulated, brief “look-ahead” similar to how interpreters anticipate what might come next in a sentence — the model assesses if additional context would change its next translation output. 通过利用准未来信息（pseudo-future information），即一种模拟的、短暂的“预测”能力，类似于口译员预测句子中将会出现的内容的能力，该模型可以评估额外的语境信息是否会改变其接下来的翻译输出。
If not, the model proceeds with translating. 如果评估结果没有变化，模型就继续翻译。
If more context is needed, it waits to “read” further. 如果需要更多背景信息，模型则会等待，进一步“读取”信息。
By using this simulated “look-ahead” information to decide the best timing for each read/write action, PsFuture achieves real-time translation with minimal delay, providing accuracy and adaptability similar to highly trained adaptive models, but without their training requirements, the researchers noted. 研究人员指出，通过利用这种模拟“预测”信息来决定每次读写操作的最佳时机，PsFuture可以在延迟最小的情况下实现实时翻译，其准确性和适应性可以媲美训练有素的自适应模型，却不需要达到自适应模型的训练要求。
“To our knowledge, PsFuture is the only adaptive method in the current SiMT field that offers such flexibility,” they said. 研究人员表示：“据我们了解，PsFuture是实时机器翻译领域中唯一具有这种灵活性的自适应方法。”
Alongside PsFuture, the researchers developed Prefix-to-Full (P2F) training, a method that prepares offline models for real-time translation tasks. 除了PsFuture，研究人员还开发了从前缀到完整（P2F）训练法，这是一种训练离线模型为实时翻译任务做准备的方法。
Offline translation models are typically trained to process an entire sentence and therefore struggle with real-time requirements. 离线翻译模型通常是为处理整个句子而训练的，因此难以满足实时翻译要求。
P2F training helps these models translate sentence fragments, or prefixes, which makes them more suitable for SiMT applications that need quick response times without sacrificing quality. P2F训练法可帮助这些模型翻译句子片段，又称前缀，因此，这些模型能更好地适配需要快速响应时间而又不牺牲质量的应用。
Slightly More Processing
处理量略有增加
The researchers compared PsFuture against previous approaches for three language pairs — Chinese-English, German-English, and English-Vietnamese — and reported that PsFuture demonstrated strong results across all three language pairs.
研究人员将PsFuture与针对中英、徳英和英越三种语言对的传统处理方法进行了比较，结果表明，PsFuture在三种语言对中都取得了优异的成绩。
Specifically, they found that PsFuture matches the performance of established adaptive policies that rely on extensive training.
具体来说，研究人员发现PsFuture在性能方面与依赖大量训练的现有适应性策略不相上下。
They also noted that PsFuture’s zero-shot approach reduces latency between source input and translation output while making SiMT more accessible and computationally efficient for widespread use.
他们还指出，PsFuture的零样本方法缩短了源语言输入和翻译输出之间的延迟，让实时机器翻译更易于广泛使用，并提高了计算效率。
Although promising, PsFuture has a minor trade-off: it requires slightly more processing to handle each read/write decision, which could affect performance on very long texts.
尽管PsFuture的前景光明，但它也面临一个小问题：在处理每个读写决策时，PsFuture需要略微增加处理量，这可能会影响较长文本方面的表现。
However, the researchers emphasize that PsFuture’s reduced need for training and computational resources makes it a “simple yet effective” solution for most SiMT applications.
不过，研究人员强调，由于PsFuture对训练和计算资源的需求减少，在大多数情况下，它可以成为实时机器翻译“简单而有效”的解决方案。
They also highlighted PsFuture’s versatility, as it can be directly applied to most existing simultaneous translation models.
他们特别指出PsFuture的广泛用途，即可以直接应用于大多数现有的同声传译模型。
“The PsFuture approach is versatile, compatible with most translation models,” they said.
研究人员表示：“PsFuture方法的用途广泛，能与大部分翻译模型兼容。”
The code will be soon available on GitHub.
有关代码将很快在GitHub上发布。
特别说明：本文仅用于学术交流，如有侵权请后台联系小编删除。
