An Empirical Investigation of Structured Output Modelingfor Graph-based Neural Dependency Parsing
Abstract
In this paper, we investigate the aspect of
structured output modeling for the state-ofthe-art graph-based neural dependency parser
(Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show
that global output-structured models can generally obtain better performance, especially on
the metric of sentence-level Complete Match.
However, probably because neural models already learn good global views of the inputs,
the improvement brought by structured output
modeling is modest.