Self-Training without Reranking for Parser Domain Adaptation and Its Impact on Semantic Role Labeling

We compare self-training with and without reranking for parser domain adaptation, and examine the impact of syntactic parser adaptation on a semantic role labeling system. Although self-training without reranking has been found not to improve in-domain accuracy for parsers trained on the WSJ Penn Treebank, we show that it is surprisingly effective for parser domain adaptation. We also show that simple self-training of a syntactic parser improves out-of-domain accuracy of a semantic role labeler.