Abstract
In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The NMT models are at different levels, have different attention mechanisms, and different neural network architectures. Our results show that NMT models are much better than SMT models in terms of character error rate. The vanilla RNNs are competitive to GRUs/LSTMs in historical spelling normalization. Transformer models perform better only when provided with more training data. We also find that subword-level models with a small subword vocabulary are better than character-level models. In addition, we propose a hybrid method which further improves the performance of historical spelling normalization.
Abstract (translated)
在本文中,我们将不同的NMT模型应用于英语,德语,匈牙利语,冰岛语和瑞典语五种语言的历史拼写规范化问题。 NMT模型处于不同的层次,具有不同的关注机制和不同的神经网络架构。我们的结果表明NMT模型在字符错误率方面比SMT模型好得多。在历史拼写规范化过程中,香草RNN对GRU / LSTM具有竞争力。只有提供更多的训练数据时,变压器模型才能表现更好。我们还发现,具有小字词表的子字级模型比字符级模型更好。另外,我们提出了一种混合方法,它进一步提高了历史拼写规范化的性能。
URL
https://arxiv.org/abs/1806.05210