Faster Parsing by Supertagger Adaptation
Faster Parsing by Supertagger Adaptation
复制标题
DOI：
--
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Jonathan K. Kummerfeld;Jessika Roesner;Tim Dawborn;J. Haggerty;J. Curran;S. Clark
中科院分区：
文献类型：
--
作者：
Jonathan K. Kummerfeld;Jessika Roesner;Tim Dawborn;J. Haggerty;J. Curran;S. Clark
我们提出了一种新的自我训练方法的分析器，它使用词汇化的语法和supertagger，专注于提高分析器的速度，而不是它的准确性。这个想法是在大量的解析器输出上训练超级标记器，这样超级标记器就可以学习提供解析器最终选择作为最高得分派生的一部分的超级标记。由于supertagger总体上提供更少的supertag，因此提高了解析速度。我们证明了该方法的有效性，使用CCG supertagger和解析器，获得显着的速度增加报纸文本的准确性没有损失。我们还表明，该方法可用于使CCG解析器适应新领域，从而提高维基百科和生物医学文本的准确性和速度。
We propose a novel self-training method for a parser which uses a lexicalised grammar and supertagger, focusing on increasing the speed of the parser rather than its accuracy. The idea is to train the supertagger on large amounts of parser output, so that the supertagger can learn to supply the supertags that the parser will eventually choose as part of the highest-scoring derivation. Since the supertagger supplies fewer supertags overall, the parsing speed is increased. We demonstrate the effectiveness of the method using a CCG supertagger and parser, obtaining significant speed increases on newspaper text with no loss in accuracy. We also show that the method can be used to adapt the CCG parser to new domains, obtaining accuracy and speed improvements for Wikipedia and biomedical text.