no code implementations • WS 2017 • Bich-Ngoc Do, Ines Rehbein, Anette Frank
We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German.
no code implementations • WS 2017 • Bich-Ngoc Do, Ines Rehbein
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history.
no code implementations • LREC 2020 • Peter Fankhauser, Bich-Ngoc Do, Marc Kupietz
We evaluate a graph-based dependency parser on DeReKo, a large corpus of contemporary German.
no code implementations • ACL 2020 • Bich-Ngoc Do, Ines Rehbein
We show that the GCN not only outperforms previous models on English but is the only model that is able to improve results over the baselines on German and Czech.
no code implementations • COLING 2020 • Bich-Ngoc Do, Ines Rehbein
In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system{'}s output to the output of a full syntactic parser leads to an overly optimistic assessment of the results.