Improving Zero-Shot-Learning for German Particle Verbs by using Training-Space Restrictions and Local Scaling
Maximilian Köper, Sabine Schulte im Walde, Max Kisselew, Sebastian Padó · 2016
Recent models in distributional semantics consider derivational patterns (e.g., use → use + f ul ) as the result of a compositional process, where base term and affix are combined.We exploit such models for German particle verbs (PVs), and focus on the task of learning a mapping function between base verbs and particle verbs.Our models apply particle-verb motivated training-space restrictions relying on nearest neighbors, as well as recent advances from zeroshot-learning.The models improve the mapping between base terms and derived terms for a new PV derivation dataset, and also across existing derivation datasets for German and English.