Incremental Learning of Context Free Grammars
Incremental Learning of Context Free Grammars
复制标题
上下文无关语法的增量学习
DOI：
10.1007/3-540-45790-9_14
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
Masashi Matsumoto
中科院分区：
文献类型：
--
作者：
Katsuhiko Nakamura;Masashi Matsumoto
本文描述了由正、负样本串合成上下文无关文法的归纳推理，并在Synapessis系统中实现。为了有效地进行文法推理，Synapse采用了以下机制：1.一种称为“归纳Cyk算法”的规则生成方法，它生成解析正样本所需的最小产生式规则。2.增量学习，将新生成的规则添加到先前获得的规则中。Synapse可以综合歧义文法和无歧义文法。实验结果表明，Synapse系统在合成上下文无关文法方面有了新的改进。
This paper describes inductive inference for synthesizing context free grammars from positive and negative sample strings, implemented inSynapsesystem. For effective inference of grammars, Synapse employs the following mechanisms.1.A rule generating method called “inductive CYK algorithm,” which generates minimum production rules required for parsing positive samples.2.Incremental learning for adding newly generated rules to previously obtained rules.Synapse can synthesize both ambiguous grammars and unambiguous grammars. Experimental results show recent improvement of Synapse system to synthesize context free grammars.