论文标题
自动预测中世纪阿拉伯语
Automated Prediction of Medieval Arabic Diacritics
论文作者
论文摘要
这项研究使用了一种角色级别的神经机器翻译方法，该方法对基于短期记忆的长期双向复发性神经网络结构进行了训练，以对中世纪的阿拉伯语进行大变化。结果从用作基线的在线工具改善。通过PYPI和Zenodo上可用的Python软件包公开发布了变音模型。我们发现，在优化可行的预测模型时应考虑上下文大小。
This study uses a character level neural machine translation approach trained on a long short-term memory-based bi-directional recurrent neural network architecture for diacritization of Medieval Arabic. The results improve from the online tool used as a baseline. A diacritization model have been published openly through an easy to use Python package available on PyPi and Zenodo. We have found that context size should be considered when optimizing a feasible prediction model.
