Multi-paraphrase Augmentation to Leverage Neural Caption Translation
Multi-paraphrase Augmentation to Leverage Neural Caption Translation
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Johanes Effendi;S. Sakti;Katsuhito Sudoh;Satoshi Nakamura
中科院分区：
文献类型：
--
作者：
Johanes Effendi;S. Sakti;Katsuhito Sudoh;Satoshi Nakamura
在机器翻译中，释义被证明可以提高翻译质量，并且随着统计机器翻译的发展而得到了广泛的研究。在本文中，我们研究和利用神经释义，以提高翻译质量的神经机器翻译（NMT），这还没有太多的探索。我们的第一个贡献是提出了一种新的方法来创建一个多释义语料库，通过视觉描述。在此之后，我们还提出了构建神经释义模型，启动专家模型，并利用它们来利用NMT。在这里，我们通过使用基于图像的释义来扩散图像信息，而不使用图像本身。我们提出的基于图像的多释义增强策略显示出对香草NMT基线的改进。
Paraphrasing has been proven to improve translation quality in machine translation (MT) and has been widely studied alongside with the development of statistical MT (SMT). In this paper, we investigate and utilize neural paraphrasing to improve translation quality in neural MT (NMT), which has not yet been much explored. Our first contribution is to propose a new way of creating a multi-paraphrase corpus through visual description. After that, we also proposed to construct neural paraphrase models which initiate expert models and utilize them to leverage NMT. Here, we diffuse the image information by using image-based paraphrasing without using the image itself. Our proposed image-based multi-paraphrase augmentation strategies showed improvement against a vanilla NMT baseline.