Improving historical spelling normalization with bi-directional LSTMs and multi-task learning
Marcel Bollmann, Anders Søgaard · Research at the University of Copenhagen (University of Copenhagen) · 2016
Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data.A common approach is to normalize the spelling of historical words to modern forms.We explore the suitability of a deep neural network architecture for this task, particularly a deep bi-LSTM network applied on a character level.Our model compares well to previously established normalization algorithms when evaluated on a diverse set of texts from Early New High German.We show that multi-task learning with additional normalization data can improve our model's performance further.