Association Metrics in Neural Transition-Based Dependency Parsing

Abstract

Lexical preferences encoded as association metrics have been shown to improve performance on structural ambiguities that are still challenging for modern parsers. This paper introduces a mechanism to include lexical preferences into a neural transition-based dependency parser for German. We compare pointwise mutual information (PMI) and embedding-based scores. Both the PMI-based model and the embedding-based model outperform the baseline significantly. The best model is PMI-based and increases overall performance by 0.26 LAS points over the baseline.