通过对抗学习利用低资源神经机器翻译中的多语言特性
Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning
AI总结：
提出DAASI方法通过学习多语言潜在表示进行句子插值，并结合Wasserstein-GAN计算奖励优化多语言NMT模型，在低资源翻译上提升4 BLEU点且在零样本场景表现鲁棒。
摘要：
生成对抗网络（GAN）为神经机器翻译（NMT）提供了一种有前景的方法。然而，在训练期间将多种形态语言输入单一模型会降低NMT的性能。在GAN中，与双语模型类似，多语言NMT在模型训练期间仅考虑每个句子的一种参考翻译。这种单一参考翻译限制了GAN模型学习关于源句子表示的充分信息。因此，在本文中，我们提出基于去噪对抗自编码器的句子插值（DAASI）方法，通过学习多语言语言对源句子和目标句子的中间潜在表示来执行句子插值。除了潜在表示外，我们还通过结合多种语言的模型生成句子进行奖励计算，将Wasserstein-GAN方法用于多语言NMT模型。这种计算出的奖励以有效的方式优化了基于GAN的多语言模型的性能。我们在低资源语言对上展示了实验，发现我们的方法优于现有的多语言NMT最先进方法，性能提升高达4 BLEU点。此外，我们在无监督场景下将训练好的模型用于零样本语言对，并展示了所提方法的鲁棒性。
英文摘要：
Generative Adversarial Networks (GAN) offer a promising approach for Neural Machine Translation (NMT). However, feeding multiple morphologically languages into a single model during training reduces the NMT's performance. In GAN, similar to bilingual models, multilingual NMT only considers one reference translation for each sentence during model training. This single reference translation limits the GAN model from learning sufficient information about the source sentence representation. Thus, in this article, we propose Denoising Adversarial Auto-encoder-based Sentence Interpolation (DAASI) approach to perform sentence interpolation by learning the intermediate latent representation of the source and target sentences of multilingual language pairs. Apart from latent representation, we also use the Wasserstein-GAN approach for the multilingual NMT model by incorporating the model generated sentences of multiple languages for reward computation. This computed reward optimizes the performance of the GAN-based multilingual model in an effective manner. We demonstrate the experiments on low-resource language pairs and find that our approach outperforms the existing state-of-the-art approaches for multilingual NMT with a performance gain of up to 4 BLEU points. Moreover, we use our trained model on zero-shot language pairs under an unsupervised scenario and show the robustness of the proposed approach.
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。
