Neural End-to-end Coreference Resolution for German in Different Domains

Hans Ole Hatzel, Fynn Schröder, Chris Biemann

Abstract: We apply neural coreference resolution to German, surpassing the previous state-of-the-art performance by a wide margin of 10–30 points F1 across three established datasets for German. This is achieved by a neural end-to-end approach, training contextual word-embeddings jointly with mention and entity similarity scores. We explore the impact of various parameters such as language models, pre-training and computational limits with respect to German data. In an effort to support datasets representing the domains of both news and literature, we make use of two distinct model architectures: a mention linking-based and an incremental entity-based approach that shouldscale to very long documents such as literary works. Our code and ready-to-use models are publicly available.