Exploiting Diversity in Natural Language Processing: Combining Parsers
Computation and Language
2007-05-23 v1
Abstract
Three state-of-the-art statistical parsers are combined to produce more accurate parses, as well as new bounds on achievable Treebank parsing accuracy. Two general approaches are presented and two combination techniques are described for each approach. Both parametric and non-parametric models are explored. The resulting parsers surpass the best previously published performance results for the Penn Treebank.
Cite
@article{arxiv.cs/0006003,
title = {Exploiting Diversity in Natural Language Processing: Combining Parsers},
author = {John C. Henderson and Eric Brill},
journal= {arXiv preprint arXiv:cs/0006003},
year = {2007}
}
Comments
8 pages