arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14109cs.CL
收藏

鲁棒神经机器翻译中的对抗子词正则化

Adversarial Subword Regularization for Robust Neural Machine Translation

Korea University(高丽大学)

Jungsoo Park, Mujeen Sung, Jinhyuk Lee, Jaewoo Kang

摘要:

将不同的子词切分暴露给神经机器翻译(NMT)模型通常提高了机器翻译的鲁棒性,因为NMT模型可以经历各种候选子词。然而,子词切分的多样化主要依赖于预训练的子词语言模型,从该预训练的子词语言模型中,不太可能对未看见的词的错误切分进行采样。在本文中,我们提出了对抗子词正则化(ADVSR),以研究在训练过程中的梯度信号是否可以作为一个替代标准,暴露不同的子词切分。我们的实验表明,我们基于模型的对抗样本有效地鼓励NMT模型对分割错误不太敏感,并提高了NMT模型在低资源和域外数据集中的性能。

英文摘要:

Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show that our model-based adversarial samples effectively encourage NMT models to be less sensitive to segmentation errors and improve the performance of NMT models in low-resource and out-domain datasets.

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。

↑