Hierarchical Search for Parsing

Hierarchical Search for Parsing
复制标题

分层搜索解析

DOI:
--
复制
发表时间:
2009
期刊:
North American Chapter of the Association for Computational Linguistics
影响因子:
--
通讯作者:
D. Klein
D. Klein
中科院分区:
--
文献类型:
--
作者:
Adam Pauls;D. Klein

文献摘要

被引文献

相似文献

从粗到细和 A* 解析都使用简单的语法来指导复杂语法中的搜索。我们在一个基于议程的通用框架中比较这两种方法,展示每种方法的权衡和相对优势。总体而言,对于中等水平的搜索错误,从粗到细的速度要快得多,但低于某个阈值 A* 更优越。此外,我们提出了关于分层 A* 解析的第一个实验,其中启发式计算本身是由元启发式指导的。多级层次结构对这两种方法都有帮助,但由于 A* 启发法中累积的松弛,在从粗到细的情况下更有效。
Both coarse-to-fine and A* parsing use simple grammars to guide search in complex ones. We compare the two approaches in a common, agenda-based framework, demonstrating the tradeoffs and relative strengths of each method. Overall, coarse-to-fine is much faster for moderate levels of search errors, but below a certain threshold A* is superior. In addition, we present the first experiments on hierarchical A* parsing, in which computation of heuristics is itself guided by meta-heuristics. Multi-level hierarchies are helpful in both approaches, but are more effective in the coarse-to-fine case because of accumulated slack in A* heuristics.