Self-training without reranking for parser domain adaptation and its impact on semantic role labeling
DANLP 2010: Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing(2010)
摘要
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.
更多查看译文
关键词
parser domain adaptation,syntactic parser,syntactic parser adaptation,simple self-training,in-domain accuracy,out-of-domain accuracy,semantic role,semantic role labeler,WSJ Penn Treebank
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络