GermEval 2014

Named Entity Recognition in German at KONVENS 2014

UKP participated in the shared task of GermEval at KONVENS 2014. In this task, systems were expected to automatically annotate nested named entities in German. For the shared task, a new dataset with sentences from German news articles and Wikipedia was created. Our system is based on state-of-the-art deep neural networks combined with specifically designed features. The system achieves an F1-measure of 75.1% and is placed 2nd among 11 systems.

Further information on the dataset can be found on the GemEval website.

Word Embeddings for German

For our task we trained word embeddings using Word2Vec on a large German corpus of about 116 Million sentences. You can use these word embeddings for your research under the CC-By license:

Download Word Embeddings with min. count 5 (1.2 GB)

Download Word Embeddings with min. count 50 (242 MB) [alternative download as word2Vec binary format (254mb)]

Download Word Embeddings with min. count 100 (151 MB) [alternative download as word2Vec binary format (158mb)]

Readme

If you use these word embeddings, please cite our paper GermEval-2014: Nested Named Entity Recognition with Neural Networks.

Contact

In case of any questions, feel free to contact Nils Reimers.

Nils Reimers, Judith Eckle-Kohler, Carsten Schnober, Jungi Kim and Iryna Gurevych. 2014. GermEval-2014: Nested Named Entity Recognition with Neural Networks. In Proceedings of the KONVENS GermEval Shared Task on Named Entity Recognition, Hildesheim, Germany.