arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04411cs.CL
收藏

面向神经机器翻译的不确定性语义增强

Uncertainty-Aware Semantic Augmentation for Neural Machine Translation

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Machine Intelligence Technology Lab, Alibaba Group(阿里巴巴集团机器智能技术实验室)

Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Luxi Xing, Weihua Luo

摘要:

神经机器翻译(NMT)作为一种序列到序列生成任务,自然包含内在的不确定性,其中一种语言中的单个句子在另一种语言中具有多个有效的对应物。然而,NMT的主流方法仅从平行语料库中观察其中一个用于模型训练,而在推理时必须处理相同意义下的足够变化。这导致训练和推理阶段之间的数据分布的差异。为了解决这个问题,我们提出了不确定性感知的语义增强,它明确地捕捉多个语义等价的源句子之间的通用语义信息,并增强隐藏的表示与此信息更好的翻译。对各种翻译任务的大量实验表明,我们的方法显着优于强基线和现有的方法。

英文摘要:

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for NMT only observe one of them from the parallel corpora for the model training but have to deal with adequate variations under the same meaning at inference. This leads to a discrepancy of the data distribution between the training and the inference phases. To address this problem, we propose uncertainty-aware semantic augmentation, which explicitly captures the universal semantic information among multiple semantically-equivalent source sentences and enhances the hidden representations with this information for better translations. Extensive experiments on various translation tasks reveal that our approach significantly outperforms the strong baselines and the existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑