Probabilistic Parsing Using Left Corner Language Models
cmp-lg
2007-05-23 v1 计算与语言
摘要
We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the underlying theory and explain how a grammar can be induced from analyzed data. We show that the left-corner approach provides an advantage over simple top-down probabilistic context-free grammars in parsing the Wall Street Journal using a grammar induced from the Penn Treebank. We also conclude that the Penn Treebank provides a fairly weak testbed due to the flatness of its bracketings and to the obvious overgeneration and undergeneration of its induced grammar.
引用
@article{arxiv.cmp-lg/9711003,
title = {Probabilistic Parsing Using Left Corner Language Models},
author = {Christopher D. Manning and Bob Carpenter},
journal= {arXiv preprint arXiv:cmp-lg/9711003},
year = {2007}
}
备注
12 pages, uses iwpt97.sty