Neural machine translation (NMT) has achieved remarkable success in producing high-quality translations. However, current NMT systems suffer from a lack of reliability, as their outputs that are often affected by lexical or syntactic changes in inputs, resulting in large variations in quality. This limitation hinders the practicality and trustworthiness of NMT. A contributing factor to this problem is that NMT models trained with the one-to-one paradigm struggle to handle the source diversity phenomenon, where inputs with the same meaning can be expressed differently. In this work, we treat this problem as a bilevel optimization problem and present a consistency-aware meta-learning (CAML) framework derived from the model-agnostic meta-learning (MAML) algorithm to address it. Specifically, the NMT model with CAML (named CoNMT) first learns a consistent meta representation of semantically equivalent sentences in the outer loop. Subsequently, a mapping from the meta representation to the output sentence is learned in the inner loop, allowing the NMT model to translate semantically equivalent sentences to the same target sentence. We conduct experiments on the NIST Chinese to English task, three WMT translation tasks, and the TED M2O task. The results demonstrate that CoNMT effectively improves overall translation quality and reliably handles diverse inputs.
翻译:具备一致性感知元学习的可靠神经机器翻译
神经机器翻译(NMT)在产生高质量翻译方面取得了显著进展,然而,目前的NMT系统缺乏可靠性,它们的输出通常受到输入中词汇或语法变化的影响,导致质量出现显著差异,这一限制阻碍了NMT的实用性和可信度。这个问题的一个因素在于使用一对一方式训练的NMT模型很难处理具有相同含义但不同表述的输入。在这项工作中,我们将这个问题视为一个双层优化问题,并提出了一种基于模型无关的元学习(MAML)算法的一致性感知元学习(CAML)框架来解决这个问题。具体而言,CAML NMT模型(称为CoNMT)首先在外循环中学习一致的元表示,表示具有语义等价的句子。随后,在内循环中学习从元表示到输出句子的映射,从而使NMT模型将语义等价的句子翻译为相同的目标句子。我们在NIST中文-英文任务,三个WMT翻译任务和TED M2O任务上进行实验。结果表明,CoNMT有效地提高了整体翻译质量并可靠地处理多样化的输入。