Semi-Supervised Neural Networks for Nested Named Entity Recognition

In this paper, we investigate a semi-supervised learning approach based on neural networks for nested named entity recognition on the GermEval 2014 dataset. The dataset consists of triples of a word, a named entity associated with that word in the first-level and one in the second-level. Additionally, the tag distribution is highly skewed, that is, the number of occurrences of certain types of tags is too small. Hence, we present a unified neural network architecture to deal with named entities in both levels simultaneously and to improve generalization performance on the classes that have a small number of labelled examples.