Annotation of Fine-Grained Geographical Entities in German Texts

We work on the creation of a corpus, crawled from the internet, on the Berlin district of Moabit, primarily meant for training NER systems in German and English. Typical NER corpora and corresponding systems distinguish persons, organisations and locations, but do not distinguish different types of location entities. For our tourism-inspired use case, we need fine-grained annotations for toponyms. In this paper, we outline the fine-grained classification of geographical entities, the resulting annotations and we present preliminary results on automatically tagging toponyms in a small, bootstrapped gold corpus.