Multi-task learning (MTL) and transfer learning (TL) are techniques to overcome the issue of data scarcity when training state-of-theart neural networks. However, finding beneficial auxiliary datasets for MTL or TL is a time-and resource-consuming trial-and-error approach. We propose new methods to automatically assess the similarity of sequence tagging datasets to identify beneficial auxiliary data for MTL or TL setups. Our methods can compute the similarity between any two sequence tagging datasets, i.e. they do not need to be annotated with the same tagset or multiple labels in parallel. Additionally, our methods take tokens and their labels into account, which is more robust than only using either of them as an information source, as conducted in prior work. We empirically show that our similarity measures correlate with the change in test score of neural networks that use the auxiliary dataset for MTL to increase the main task performance. We provide an efficient, opensource implementation. 1 2 Related work 2.1 Neural multi-task and transfer learning Multi-task learning (MTL) is a technique to learn multiple tasks jointly (Caruana, 1997). Depending on the setting, either all tasks are equally important, or only the performance on the main task is of interest, which shall be improved with additional training data. MTL has been successfully applied in natural language processing for various sequence tagging tasks (

In this paper we describe the system submitted by UHH to the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. We propose a neural architecture based on the concepts of UZH (Makarov et al., 2017), adding new ideas and techniques to their key concept and evaluating different combinations of parameters. The resulting system is a language-agnostic network model that aims to reduce the number of learned edit operations by introducing equivalence classes over graphical features of individual characters. We try to pinpoint advantages and drawbacks of this approach by comparing different network configurations and evaluating our results over a wide range of languages.