论文标题
朝向端到端内图像神经机器翻译
Towards End-to-End In-Image Neural Machine Translation
论文作者
论文摘要
在本文中，我们对图像机器翻译的任务进行初步调查：将包含一种语言文本的图像转换为包含另一种语言相同文本的图像。我们为这项任务提出了一个端到端的神经模型，该模型受到最近的神经机器翻译方法的启发，并纯粹基于像素级的监督，证明了有希望的初始结果。然后，我们对系统输出进行定量和定性评估，并讨论一些常见的故障模式。最后，我们以未来工作的指示得出结论。
In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing the same text in another language. We propose an end-to-end neural model for this task inspired by recent approaches to neural machine translation, and demonstrate promising initial results based purely on pixel-level supervision. We then offer a quantitative and qualitative evaluation of our system outputs and discuss some common failure modes. Finally, we conclude with directions for future work.
