microNER: A Micro-Service for German Named Entity Recognition based on BiLSTM-CRF
This work addresses NER for German language applications, providing a micro-service for easy integration, but it is incremental as it applies existing methods to a less-studied domain.
The paper tackled the problem of named entity recognition (NER) in German texts by evaluating different word and character embeddings, achieving F-scores above 82% on GermEval'14 and above 85% on CoNLL'03, which is near state-of-the-art performance.
For named entity recognition (NER), bidirectional recurrent neural networks became the state-of-the-art technology in recent years. Competing approaches vary with respect to pre-trained word embeddings as well as models for character embeddings to represent sequence information most effectively. For NER in German language texts, these model variations have not been studied extensively. We evaluate the performance of different word and character embeddings on two standard German datasets and with a special focus on out-of-vocabulary words. With F-Scores above 82% for the GermEval'14 dataset and above 85% for the CoNLL'03 dataset, we achieve (near) state-of-the-art performance for this task. We publish several pre-trained models wrapped into a micro-service based on Docker to allow for easy integration of German NER into other applications via a JSON API.