Refine
Year of publication
- 2017 (1)
Document Type
Language
- English (1)
Has Fulltext
- yes (1)
Is part of the Bibliography
- yes (1) (remove)
Keywords
- Automatische Sprachverarbeitung (1) (remove)
Publicationstate
- Veröffentlichungsversion (1) (remove)
Reviewstate
- Peer-Review (1)
Publisher
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker).